NeurIPS(NIPS) 2019 论文列表
Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada.
|
Mixtape: Breaking the Softmax Bottleneck Efficiently.
Enabling hyperparameter optimization in sequential autoencoders for spiking neural data.
Re-randomized Densification for One Permutation Hashing and Bin-wise Consistent Weighted Sampling.
Self-attention with Functional Time Representation Learning.
Surround Modulation: A Bio-inspired Connectivity Structure for Convolutional Neural Networks.
On the equivalence between graph isomorphism testing and function approximation with GNNs.
On Relating Explanations and Adversarial Examples.
Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximation.
Generalization in multitask deep neural classifiers: a statistical physics approach.
Ease-of-Teaching and Language Structure from Emergent Communication.
Approximate Feature Collisions in Neural Nets.
The Geometry of Deep Networks: Power Diagram Subdivision.
Generative Models for Graph-Based Protein Design.
PIDForest: Anomaly Detection via Partial Identification.
Space and Time Efficient Kernel Density Estimation in High Dimensions.
Abstraction based Output Range Analysis for Neural Networks.
Exploring Algorithmic Fairness in Robust Graph Covering Problems.
Learning Data Manipulation for Augmentation and Weighting.
Imitation-Projected Programmatic Reinforcement Learning.
On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset.
Gradient-based Adaptive Markov Chain Monte Carlo.
Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models.
BehaveNet: nonlinear embedding and Bayesian neural decoding of behavioral videos.
Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics.
Are deep ResNets provably better than linear predictors?
Inherent Tradeoffs in Learning Fair Representations.
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty.
A Family of Robust Stochastic Operators for Reinforcement Learning.
End-to-End Learning on 3D Protein Structure for Interface Prediction.
Universality and individuality in neural dynamics across large populations of recurrent networks.
TAB-VCR: Tags and Attributes based VCR Baselines.
Wasserstein Dependency Measure for Representation Learning.
Fast structure learning with modular regularization.
Exact Combinatorial Optimization with Graph Convolutional Neural Networks.
Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks.
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity.
Amortized Bethe Free Energy Minimization for Learning MRFs.
Learning Representations by Maximizing Mutual Information Across Views.
Learning Reward Machines for Partially Observable Reinforcement Learning.
Stacked Capsule Autoencoders.
Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain Activity.
Riemannian batch normalization for SPD neural networks.
Differential Privacy Has Disparate Impact on Model Accuracy.
Low-Rank Bandit Methods for High-Dimensional Dynamic Pricing.
A Kernel Loss for Solving the Bellman Equation.
Power analysis of knockoff filters for correlated designs.
Explicitly disentangling image content from translation and rotation with spatial-VAE.
Multiple Futures Prediction.
Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology.
Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks.
Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks.
Hamiltonian Neural Networks.
Input-Output Equivalence of Unitary and Contractive RNNs.
Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration.
DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs.
Robust exploration in linear quadratic reinforcement learning.
Goal-conditioned Imitation Learning.
Certifying Geometric Robustness of Neural Networks.
DeepWave: A Recurrent Neural-Network for Real-Time Acoustic Imaging.
Flattening a Hierarchical Clustering through Active Learning.
Faster width-dependent algorithm for mixed packing and covering LPs.
Group Retention when Using Machine Learning in Sequential Decision Making: the Interplay between User Dynamics and Fairness.
Can Unconditional Language Models Recover Arbitrary Sentences?
Search on the Replay Buffer: Bridging Planning and Reinforcement Learning.
Momentum-Based Variance Reduction in Non-Convex SGD.
Flexible Modeling of Diversity with Strongly Log-Concave Distributions.
Text-Based Interactive Recommendation via Constraint-Augmented Reinforcement Learning.
Understanding Sparse JL for Feature Hashing.
Machine Learning Estimation of Heterogeneous Treatment Effects with Instruments.
Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation.
Efficient Rematerialization for Deep Networks.
Multi-Criteria Dimensionality Reduction with Applications to Fairness.
Generalization Error Analysis of Quantized Compressive Learning.
Invariance and identifiability issues for word embeddings.
Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions.
Efficiently Learning Fourier Sparse Set Functions.
An Algorithm to Learn Polytree Networks with Hidden Nodes.
Beyond the Single Neuron Convex Barrier for Neural Network Certification.
Minimal Variance Sampling in Stochastic Gradient Boosting.
Multi-task Learning for Aggregated Data using Gaussian Processes.
Semi-Parametric Efficient Policy Learning with Continuous Actions.
On Human-Aligned Risk Minimization.
Learning to Optimize in Swarms.
Surfing: Iterative Optimization Over Incrementally Trained Deep Networks.
Computational Separations between Sampling and Optimization.
Robust Bi-Tempered Logistic Loss Based on Bregman Divergences.
Locally Private Learning without Interaction Requires Separation.
Compositional Plan Vectors.
The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares.
Function-Space Distributions over Kernels.
Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain).
Semantic-Guided Multi-Attention Localization for Zero-Shot Learning.
Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods.
Offline Contextual Bandits with High Probability Fairness Guarantees.
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis.
Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumption.
Online Optimal Control with Linear Dynamics and Predictions: Algorithms and Regret Analysis.
Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs.
Generating Diverse High-Fidelity Images with VQ-VAE-2.
Don't take it lightly: Phasing optical random projections with unknown operators.
Planning with Goal-Conditioned Policies.
Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors.
Icebreaker: Element-wise Efficient Information Acquisition with a Bayesian Deep Latent Gaussian Model.
Value Function in Frequency Domain and the Characteristic Value Iteration Algorithm.
Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks.
Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness.
Deep Leakage from Gradients.
Towards Practical Alternating Least-Squares for CCA.
Sliced Gromov-Wasserstein.
Model Selection for Contextual Bandits.
A Self Validation Network for Object-Level Human Attention Estimation.
Discrete Flows: Invertible Generative Models of Discrete Data.
Likelihood Ratios for Out-of-Distribution Detection.
Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations.
Nonparametric Contextual Bandits in Metric Spaces with Unknown Metric.
Learning Compositional Neural Programs with Recursive Tree Search and Planning.
Bayesian Layers: A Module for Neural Network Uncertainty.
Exact Gaussian Processes on a Million Data Points.
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation.
Compiler Auto-Vectorization with Imitation Learning.
On the Fairness of Disentangled Representations.
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets.
Pure Exploration with Multiple Correct Answers.
Low-Complexity Nonparametric Bayesian Online Prediction with Universal Guarantees.
Policy Poisoning in Batch Reinforcement Learning and Control.
Reflection Separation using a Pair of Unpolarized and Polarized Images.
Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness.
Cormorant: Covariant Molecular Neural Networks.
Censored Semi-Bandits: A Framework for Resource Allocation with Censored Feedback.
Deep Multi-State Dynamic Recurrent Neural Networks Operating on Wavelet Based Neural Features for Robust Brain Machine Interfaces.
Implicit Posterior Variational Inference for Deep Gaussian Processes.
Non-Asymptotic Pure Exploration by Solving Games.
Implicit Regularization of Accelerated Methods in Hilbert Spaces.
Hamiltonian descent for composite objectives.
Differentially Private Distributed Data Summarization under Covariate Shift.
Efficient characterization of electrically evoked responses for neural interfaces.
Worst-Case Regret Bounds for Exploration via Randomized Value Functions.
Categorized Bandits.
Generalization Bounds in the Predict-then-Optimize Framework.
Flexible information routing in neural populations through stochastic comodulation.
Untangling in Invariant Speech Recognition.
Structure Learning with Side Information: Sample Complexity.
Characterization and Learning of Causal Graphs with Latent Variables from Soft Interventions.
General E(2)-Equivariant Steerable CNNs.
When to use parametric models in reinforcement learning?
Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization.
Robust Attribution Regularization.
Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection.
Sample Efficient Active Learning of Causal Trees.
Unsupervised Discovery of Temporal Structure in Noisy Data with Dynamical Components Analysis.
Constraint-based Causal Structure Learning with Consistent Separating Sets.
Stochastic Frank-Wolfe for Composite Convex Minimization.
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization.
Are Disentangled Representations Helpful for Abstract Visual Reasoning?
Integrating Markov processes with structural causal modeling enables counterfactual inference in complex systems.
Outlier Detection and Robust PCA Using a Convex Measure of Innovation.
Differentially Private Covariance Estimation.
A Similarity-preserving Network Trained on Transformed Images Recapitulates Salient Features of the Fly Motion Detection Circuit.
Fast, Provably convergent IRLS Algorithm for p-norm Linear Regression.
Correlation Priors for Reinforcement Learning.
Learning Positive Functions with Pseudo Mirror Descent.
Computing Linear Restrictions of Neural Networks.
Recovering Bandits.
Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning.
Inducing brain-relevant bias in natural language processing models.
Stochastic Bandits with Context Distributions.
User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning.
Reinforcement Learning with Convex Constraints.
Provable Certificates for Adversarial Examples: Fitting a Ball in the Union of Polytopes.
Universal Approximation of Input-Output Maps by Temporal Convolutional Nets.
Variational Bayesian Optimal Experimental Design.
Multi-resolution Multi-task Gaussian Processes.
Are Sixteen Heads Really Better than One?
Defending Neural Backdoors via Generative Distribution Modeling.
A New Perspective on Pool-Based Active Classification and False-Discovery Control.
Accurate Layerwise Interpretable Competence Estimation.
Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift.
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck.
An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints.
The Implicit Metropolis-Hastings Algorithm.
Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimization.
Inverting Deep Generative models, One layer at a time.
Complexity of Highly Parallel Non-Smooth Convex Optimization.
On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks.
GOT: An Optimal Transport framework for Graph comparison.
Primal-Dual Block Generalized Frank-Wolfe.
Learning Fairness in Multi-Agent Systems.
Semi-flat minima and saddle points by embedding neural networks to overparameterization.
Sampled Softmax with Random Fourier Features.
Adversarial Robustness through Local Linearization.
A Graph Theoretic Additive Approximation of Optimal Transport.
Combining Generative and Discriminative Models for Hybrid Inference.
Bayesian Optimization under Heavy-tailed Payoffs.
MonoForest framework for tree ensemble analysis.
Using Embeddings to Correct for Unobserved Confounding in Networks.
A Solvable High-Dimensional Model of GAN.
Rand-NSG: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node.
On Robustness to Adversarial Examples and Polynomial Optimization.
Towards Hardware-Aware Tractable Learning of Probabilistic Models.
Towards modular and programmable architecture search.
Learning about an exponential amount of conditional distributions.
A neurally plausible model learns successor representations in partially observable environments.
AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters.
A New Distribution on the Simplex with Auto-Encoding Applications.
Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems.
Compacting, Picking and Growing for Unforgetting Continual Learning.
An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors.
Paraphrase Generation with Latent Bag of Words.
Alleviating Label Switching with Optimal Transport.
No-Regret Learning in Unknown Games with Correlated Payoffs.
Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics.
Communication trade-offs for Local-SGD with large step size.
Explanations can be manipulated and geometry is to blame.
Graph Normalizing Flows.
RUDDER: Return Decomposition for Delayed Rewards.
Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions.
Search-Guided, Lightly-Supervised Training of Structured Prediction Energy Networks.
Specific and Shared Causal Relation Modeling and Mechanism-Based Clustering.
Object landmark discovery through unsupervised adaptation.
Globally Optimal Learning for Structured Elliptical Losses.
Shaping Belief States with Generative Environment Models for RL.
Exploration via Hindsight Goal Generation.
Hierarchical Optimal Transport for Multimodal Distribution Alignment.
Cold Case: The Lost MNIST Digits.
Recurrent Kernel Networks.
Optimal Sampling and Clustering in the Stochastic Block Model.
ODE2VAE: Deep generative second order ODEs with Bayesian neural networks.
Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes.
Manifold denoising by Nonlinear Robust Principal Component Analysis.
On Differentially Private Graph Sparsification and Applications.
Global Convergence of Gradient Descent for Deep Linear Residual Networks.
Variational Bayes under Model Misspecification.
Deep Random Splines for Point Process Intensity Estimation of Neural Population Data.
Diffusion Improves Graph Learning.
Learning Multiple Markov Chains via Adaptive Allocation.
Metalearned Neural Memory.
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning.
Variance Reduction in Bipartite Experiments through Correlation Clustering.
Privacy Amplification by Mixing and Diffusion Mechanisms.
The continuous Bernoulli: fixing a pervasive error in variational autoencoders.
A Fourier Perspective on Model Robustness in Computer Vision.
Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products.
Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Game.
Online Convex Matrix Factorization with Representative Regions.
Assessing Social and Intersectional Biases in Contextualized Word Representations.
Learning nonlinear level sets for dimensionality reduction in function approximation.
Outlier-robust estimation of a sparse linear model using \ell_1-penalized Huber's M-estimator.
Near Neighbor: Who is the Fairest of Them All?
Kalman Filter, Sensor Fusion, and Constrained Regression: Equivalences and Insights.
Modeling Conceptual Understanding in Image Reference Games.
Communication-efficient Distributed SGD with Sketching.
A Simple Baseline for Bayesian Uncertainty in Deep Learning.
Episodic Memory in Lifelong Language Learning.
Biases for Emergent Communication in Multi-agent Reinforcement Learning.
Learning step sizes for unfolded sparse coding.
Online-Within-Online Meta-Learning.
Generative Well-intentioned Networks.
Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match.
Learning to Correlate in Multi-Player General-Sum Sequential Games.
Unified Language Model Pre-training for Natural Language Understanding and Generation.
The Option Keyboard: Combining Skills in Reinforcement Learning.
A Composable Specification Language for Reinforcement Learning Tasks.
Convergence of Adversarial Training in Overparametrized Neural Networks.
Provably robust boosted decision stumps and trees against adversarial attacks.
Generalization Bounds for Neural Networks via Approximate Description Length.
Fast and Furious Learning in Zero-Sum Games: Vanishing Regret with Non-Vanishing Step Sizes.
Minimum Stein Discrepancy Estimators.
Piecewise Strong Convexity of Neural Networks.
Self-Supervised Deep Learning on Point Clouds by Reconstructing Space.
Sim2real transfer learning for 3D human pose estimation: motion to the rescue.
REM: From Structural Entropy to Community Structure Deception.
Kernel quadrature with DPPs.
Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices.
Cross-Domain Transferability of Adversarial Perturbations.
On the Inductive Bias of Neural Tangent Kernels.
Triad Constraints for Learning Causal Structure of Latent Variables.
Sparse High-Dimensional Isotonic Regression.
Accurate, reliable and fast robustness evaluation.
Uncertainty on Asynchronous Time Event Prediction.
Recurrent Space-time Graph Neural Networks.
Random Projections and Sampling Algorithms for Clustering of High-Dimensional Polygonal Curves.
k-Means Clustering of Lines for Big Data.
Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs.
Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation.
Streaming Bayesian Inference for Crowdsourced Classification.
Learning search spaces for Bayesian optimization: Another view of hyperparameter transfer learning.
Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification.
Band-Limited Gaussian Processes: The Sinc Kernel.
Regret Bounds for Learning State Representations in Reinforcement Learning.
Unsupervised Object Segmentation by Redrawing.
Learning Hawkes Processes from a handful of events.
Causal Regularization.
Shadowing Properties of Optimization Algorithms.
Efficient Algorithms for Smooth Minimax Optimization.
Random Path Selection for Continual Learning.
Scalable Deep Generative Relational Model with High-Order Node Dependence.
MetaInit: Initializing learning by learning to initialize.
Implicit Semantic Data Augmentation for Deep Networks.
Curriculum-guided Hindsight Experience Replay.
Continuous-time Models for Stochastic Optimization Algorithms.
Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond.
Beating SGD Saturation with Tail-Averaging and Minibatching.
A Generic Acceleration Framework for Stochastic Composite Optimization.
Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders.
Selecting causal brain features with a single conditional independence test per feature.
Control What You Can: Intrinsically Motivated Task-Planning Agent.
Correlation Clustering with Adaptive Similarity Queries.
When to Trust Your Model: Model-Based Policy Optimization.
Kernelized Bayesian Softmax for Text Generation.
Efficient Identification in Linear Structural Causal Models with Instrumental Cutsets.
Hindsight Credit Assignment.
Distribution Learning of a Random Spatial Field with a Location-Unaware Mobile Sensor.
Generalization of Reinforcement Learners with Working and Episodic Memory.
Structured Variational Inference in Continuous Cox Process Models.
A General Framework for Symmetric Property Estimation.
Selective Sampling-based Scalable Sparse Subspace Clustering.
R2D2: Reliable and Repeatable Detector and Descriptor.
Exponentially convergent stochastic k-PCA without variance reduction.
Planning in entropy-regularized Markov decision processes and games.
Universality in Learning from Linear Measurements.
Root Mean Square Layer Normalization.
Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning.
Fast and Accurate Stochastic Gradient Estimation.
Towards Interpretable Reinforcement Learning Using Attention Augmented Agents.
Robustness Verification of Tree-based Models.
Comparing distributions: 퓁1 geometry improves kernel two-sample testing.
Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration.
Tree-Sliced Variants of Wasserstein Distances.
Multiagent Evaluation under Incomplete Information.
Theoretical Analysis of Adversarial Learning: A Minimax Approach.
Classification Accuracy Score for Conditional Generative Models.
Calibration tests in multi-class classification: A unifying framework.
Think out of the "Box": Generically-Constrained Asynchronous Composite Optimization and Hedging.
Multi-objective Bayesian optimisation with preferences over objectives.
Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies.
Are Labels Required for Improving Adversarial Robustness?
PAC-Bayes Un-Expected Bernstein Inequality.
Screening Sinkhorn Algorithm for Regularized Optimal Transport.
A Primal Dual Formulation For Deep Learning With Constraints.
Structured Prediction with Projection Oracles.
Integer Discrete Flows and Lossless Compression.
Bootstrapping Upper Confidence Bound.
Deep Multimodal Multilinear Fusion with High-order Polynomial Pooling.
Modelling the Dynamics of Multiagent Q-Learning in Repeated Symmetric Games: a Mean Field Theoretic Approach.
Counting the Optimal Solutions in Graphical Models.
Submodular Function Minimization with Noisy Evaluation Oracle.
A Domain Agnostic Measure for Monitoring and Evaluating GANs.
Novel positional encodings to enable tree-based transformers.
SIC-MMAB: Synchronisation Involves Communication in Multiplayer Multi-Armed Bandits.
Pareto Multi-Task Learning.
Improved Regret Bounds for Bandit Combinatorial Optimization.
Weighted Linear Bandits for Non-Stationary Environments.
Fast and Provable ADMM for Learning with Generative Priors.
Adaptive Density Estimation for Generative Models.
The Impact of Regularization on High-dimensional Logistic Regression.
Learning to Confuse: Generating Training Time Adversarial Data with Auto-Encoder.
Graph Transformer Networks.
Connections Between Mirror Descent, Thompson Sampling and the Information Ratio.
Margin-Based Generalization Lower Bounds for Boosted Classifiers.
Debiased Bayesian inference for average treatment effects.
Prediction of Spatial Point Processes: Regularized Method with Out-of-Sample Guarantees.
Adversarial Music: Real world Audio Adversary against Wake-word Detection System.
Generative Modeling by Estimating Gradients of the Data Distribution.
SPoC: Search-based Pseudocode to Code.
Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates.
Neural Attribution for Semantic Bug-Localization in Student Programs.
Online Continual Learning with Maximal Interfered Retrieval.
Theoretical evidence for adversarial robustness through randomization.
Attribution-Based Confidence Metric For Deep Neural Networks.
Gradient based sample selection for online continual learning.
Neural Relational Inference with Fast Modular Meta-learning.
Multivariate Distributionally Robust Convex Regression under Absolute Error Loss.
On the Downstream Performance of Compressed Word Embeddings.
Bayesian Optimization with Unknown Search Space.
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction.
Meta-Inverse Reinforcement Learning with Probabilistic Context Variables.
Concentration of risk measures: A Wasserstein distance approach.
Dimension-Free Bounds for Low-Precision Training.
The Case for Evaluating Causal Models Using Interventional Measures and Empirical Data.
Optimizing Generalized PageRank Methods for Seed-Expansion Community Detection.
Causal Confusion in Imitation Learning.
Rethinking Kernel Methods for Node Representation Learning on Graphs.
Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks.
Thresholding Bandit with Optimal Aggregate Regret.
Structured Graph Learning Via Laplacian Spectral Constraints.
DTWNet: a Dynamic Time Warping Network.
A Zero-Positive Learning Approach for Diagnosing Software Performance Regressions.
Uniform convergence may be unable to explain generalization in deep learning.
Policy Optimization Provably Converges to Nash Equilibria in Zero-Sum Linear Quadratic Games.
Learning Auctions with Robust Incentive Guarantees.
Subquadratic High-Dimensional Hierarchical Clustering.
Variational Temporal Abstraction.
Geometry-Aware Neural Rendering.
Exact sampling of determinantal point processes with sublinear time preprocessing.
Global Guarantees for Blind Demodulation with Generative Priors.
The Thermodynamic Variational Objective.
Identification of Conditional Causal Effects under Markov Equivalence.
Landmark Ordinal Embedding.
Necessary and Sufficient Geometries for Gradient Methods.
A Necessary and Sufficient Stability Notion for Adaptive Generalization.
Personalizing Many Decisions with High-Dimensional Covariates.
Sparse Variational Inference: Bayesian Coresets from Scratch.
Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback.
Provable Non-linear Inductive Matrix Completion.
Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks.
Smoothing Structured Decomposable Circuits.
Distributed estimation of the inverse Hessian by determinantal averaging.
Learning Neural Networks with Adaptive Regularization.
Variance Reduction for Matrix Games.
Faster Boosting with Smaller Memory.
A Direct tilde{O}(1/epsilon) Iteration Parallel Algorithm for Optimal Transport.
Online EXP3 Learning in Adversarial Bandits with Delayed Feedback.
Attentive State-Space Modeling of Disease Progression.
Privacy-Preserving Q-Learning with Functional Noise in Continuous Spaces.
Neural Temporal-Difference Learning Converges to Global Optima.
Demystifying Black-box Models with Symbolic Metamodels.
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers.
Private Stochastic Convex Optimization with Optimal Rates.
Distribution oblivious, risk-aware algorithms for multi-armed bandits with unbounded rewards.
Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test.
Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks.
NAOMI: Non-Autoregressive Multiresolution Sequence Imputation.
Meta Architecture Search.
Gaussian-Based Pooling for Convolutional Neural Networks.
Machine Teaching of Active Sequential Learners.
Unlabeled Data Improves Adversarial Robustness.
Levenshtein Transformer.
On Tractable Computation of Expected Predictions.
Adversarial Fisher Vectors for Unsupervised Representation Learning.
Greedy Sampling for Approximate Clustering in the Presence of Outliers.
Image Captioning: Transforming Objects into Words.
Learning Stable Deep Dynamics Models.
Region Mutual Information Loss for Semantic Segmentation.
Unified Sample-Optimal Property Estimation in Near-Linear Time.
Data Parameters: A New Family of Parameters for Learning a Differentiable Curriculum.
Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization.
Online Forecasting of Total-Variation-bounded Sequences.
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting.
MaxGap Bandit: Adaptive Algorithms for Approximate Ranking.
Controllable Unsupervised Text Attribute Transfer via Editing Entangled Latent Representation.
On Distributed Averaging for Stochastic k-PCA.
Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates.
MintNet: Building Invertible Neural Networks with Masked Convolutions.
The Broad Optimality of Profile Maximum Likelihood.
Exponential Family Estimation via Adversarial Dynamics Embedding.
On the (In)fidelity and Sensitivity of Explanations.
Statistical Model Aggregation via Parameter Matching.
Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks.
Improving Black-box Adversarial Attacks with a Transfer-based Prior.
Statistical Analysis of Nearest Neighbor Methods for Anomaly Detection.
On Making Stochastic Classifiers Deterministic.
How to Initialize your Network? Robust Initialization for WeightNorm & ResNets.
McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds.
Private Testing of Distributions via Sample Permutations.
Superposition of many models into one.
Random Projections with Asymmetric Quantization.
High-Dimensional Optimization in Adaptive Random Subspaces.
Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks.
Program Synthesis and Semantic Parsing with Learned Code Idioms.
Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks.
Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes.
Cross-Modal Learning with Adversarial Samples.
An Embedding Framework for Consistent Polyhedral Surrogates.
Rates of Convergence for Large-scale Nearest Neighbor Classification.
Consistency-based Semi-supervised Learning for Object detection.
Optimizing Generalized Rate Metrics with Three Players.
A Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation.
Unsupervised Learning of Object Keypoints for Perception and Control.
Semi-Implicit Graph Variational Auto-Encoders.
Variational Graph Recurrent Neural Networks.
Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering.
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence.
Sequential Experimental Design for Transductive Linear Bandits.
Splitting Steepest Descent for Growing Neural Architectures.
Transfer Learning via Minimizing the Performance Gap Between Domains.
Two Time-scale Off-Policy TD Learning: Non-asymptotic Analysis over Markovian Samples.
Deep Gamblers: Learning to Abstain with Portfolio Theory.
Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks.
Multilabel reductions: what is my loss optimising?
Oracle-Efficient Algorithms for Online Linear Optimization with Bandit Feedback.
Dimensionality reduction: theoretical perspective on practical measures.
Neural Trust Region/Proximal Policy Optimization Attains Globally Optimal Policy.
G2SAT: Learning to Generate SAT Formulas.
Large Scale Adversarial Representation Learning.
Sample Complexity of Learning Mixture of Sparse Linear Regressions.
Unsupervised Curricula for Visual Meta-Reinforcement Learning.
Learning Robust Global Representations by Penalizing Local Predictive Power.
Efficient Convex Relaxations for Streaming PCA.
Same-Cluster Querying for Overlapping Clusters.
Nearly Tight Bounds for Robust Proper Learning of Halfspaces with a Margin.
A unified variance-reduced accelerated gradient method for convex optimization.
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games.
MarginGAN: Adversarial Training in Semi-Supervised Learning.
On Fenchel Mini-Max Learning.
Statistical-Computational Tradeoff in Single Index Models.
Functional Adversarial Attacks.
Bandits with Feedback Graphs and Switching Costs.
Superset Technique for Approximate Recovery in One-Bit Compressed Sensing.
Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards.
Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models.
Discrete Object Generation with Reversible Inductive Construction.
Limits of Private Learning with Access to Public Data.
Can SGD Learn Recurrent Neural Networks with Provable Generalization?
DETOX: A Redundancy-based Framework for Faster and More Robust Gradient Aggregation.
On the Expressive Power of Deep Polynomial Neural Networks.
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization.
Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.
Learning to Self-Train for Semi-Supervised Few-Shot Classification.
Policy Continuation with Hindsight Inverse Dynamics.
Sequential Neural Processes.
STREETS: A Novel Camera Network Dataset for Traffic Flow.
Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning.
CXPlain: Causal Explanations for Model Interpretation under Uncertainty.
KNG: The K-Norm Gradient Mechanism.
Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks.
Elliptical Perturbations for Differential Privacy.
Logarithmic Regret for Online Control.
Scalable Bayesian inference of dendritic voltage via spatiotemporal recurrent state space models.
Certainty Equivalence is Efficient for Linear Quadratic Control.
Learning Mixtures of Plackett-Luce Models from Structured Partial Orders.
Unsupervised Meta-Learning for Few-Shot Image Classification.
Efficient Forward Architecture Search.
Average Case Column Subset Selection for Entrywise 퓁1-Norm Loss.
Decentralized sketching of low rank matrices.
Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization.
Metamers of neural networks reveal divergence from human perceptual systems.
Efficiently avoiding saddle points with zero order methods: No gradients required.
A Game Theoretic Approach to Class-wise Selective Rationalization.
Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond.
SHE: A Fast and Accurate Deep Neural Network for Encrypted Data.
Hierarchical Decision Making by Generating and Following Natural Language Instructions.
On Sample Complexity Upper and Lower Bounds for Exact Ranking from Noisy Comparisons.
A unified theory for the origin of grid cells through the lens of pattern formation.
Model Similarity Mitigates Test Set Overuse.
Dying Experts: Efficient Algorithms with Optimal Regret Bounds.
Transductive Zero-Shot Learning with Visual Structure Constraint.
Neural Networks with Cheap Differential Operators.
Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes.
Learning to Learn By Self-Critique.
Multi-Agent Common Knowledge Reinforcement Learning.
Residual Flows for Invertible Generative Modeling.
Meta Learning with Relational Information for Short Sequences.
On Robustness of Principal Component Regression.
Stochastic Variance Reduced Primal Dual Algorithms for Empirical Composition Optimization.
On the Value of Target Data in Transfer Learning.
Learning metrics for persistence-based summaries and applications for graph classification.
Neural Jump Stochastic Differential Equations.
A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks.
Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models.
Practical Two-Step Lookahead Bayesian Optimization.
Bayesian Joint Estimation of Multiple Graphical Models.
Compositional generalization through meta sequence-to-sequence learning.
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning.
Convergence-Rate-Matching Discretization of Accelerated Optimization Flows Through Opportunistic State-Triggered Control.
Dynamic Incentive-Aware Learning: Robust Pricing in Contextual Auctions.
Memory Efficient Adaptive Optimization.
A Benchmark for Interpretability Methods in Deep Neural Networks.
Data-dependent Sample Complexity of Deep Neural Networks via Lipschitz Augmentation.
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel.
A Bayesian Theory of Conformity in Collective Decision Making.
Evaluating Protein Transfer Learning with TAPE.
Contextual Bandits with Cross-Learning.
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling.
Guided Meta-Policy Search.
A neurally plausible model for online recognition and postdiction in a dynamical environment.
Understanding the Role of Momentum in Stochastic Gradient Methods.
Covariate-Powered Empirical Bayes Estimation.
Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer.
Lookahead Optimizer: k steps forward, 1 step back.
Learning Nearest Neighbor Graphs from Noisy Distance Samples.
Random Tessellation Forests.
Differentiable Convex Optimization Layers.
Zero-shot Knowledge Transfer via Adversarial Belief Matching.
Using Statistics to Automate Stochastic Optimization.
Learning from brains how to regularize machines.
Maximum Entropy Monte-Carlo Planning.
Sobolev Independence Criterion.
DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization.
Non-Cooperative Inverse Reinforcement Learning.
Tight Dimensionality Reduction for Sketching Low Degree Polynomial Kernels.
Certified Adversarial Robustness with Additive Noise.
ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models.
A Linearly Convergent Method for Non-Smooth Non-Convex Optimization on the Grassmannian with Applications to Robust Subspace and Dictionary Learning.
Efficient online learning with kernels for adversarial large scale problems.
Language as an Abstraction for Hierarchical Deep Reinforcement Learning.
Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse.
Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices.
ADDIS: an adaptive discarding algorithm for online FDR control with conservative nulls.
Explicit Explore-Exploit Algorithms in Continuous State Spaces.
Algorithmic Analysis and Statistical Estimation of SLOPE via Approximate Message Passing.
Multiclass Performance Metric Elicitation.
Correlation clustering with local objectives.
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias.
Sinkhorn Barycenters with Free Support via Frank-Wolfe Algorithm.
Discovery of Useful Questions as Auxiliary Tasks.
Budgeted Reinforcement Learning in Continuous State Space.
Deep Generative Video Compression.
Towards Automatic Concept-based Explanations.
A coupled autoencoder approach for multi-modal analysis of cell types.
Linear Stochastic Bandits Under Safety Constraints.
GNNExplainer: Generating Explanations for Graph Neural Networks.
Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks.
Sampling Networks and Aggregate Simulation for Online POMDP Planning.
Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback.
Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models.
(Nearly) Efficient Algorithms for the Graph Matching Problem on Correlated Random Graphs.
A Meta-Analysis of Overfitting in Machine Learning.
Write, Execute, Assess: Program Synthesis with a REPL.
Trivializations for Gradient-Based Optimization on Manifolds.
A General Theory of Equivariant CNNs on Homogeneous Spaces.
Distributionally Robust Optimization and Generalization in Kernel Methods.
Reconciling meta-learning and continual learning with online mixtures of tasks.
Limitations of Lazy Training of Two-layers Neural Network.
STAR-Caps: Capsule Networks with Straight-Through Attentive Routing.
Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses.
A Stochastic Composite Gradient Method with Incremental Variance Reduction.
Sample Adaptive MCMC.
Defending Against Neural Fake News.
Unsupervised Co-Learning on G-Manifolds Across Irreducible Representations.
Better Transfer Learning with Inferred Successor Maps.
What Can ResNet Learn Efficiently, Going Beyond Kernels?
Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems.
Neural Multisensory Scene Inference.
Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations.
Equal Opportunity in Online Classification with Partial Feedback.
Learning Bayesian Networks with Low Rank Conditional Probability Tables.
Accurate Uncertainty Estimation and Decomposition in Ensemble Learning.
Adaptively Aligned Image Captioning via Adaptive Attention Time.
This Looks Like That: Deep Learning for Interpretable Image Recognition.
Parameter elimination in particle Gibbs sampling.
PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points.
Online Learning via the Differential Privacy Lens.
Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration.
Retrosynthesis Prediction with Conditional Graph Logic Network.
Approximating the Permanent by Sampling from Adaptive Partitions.
Learning Macroscopic Brain Connectomes via Group-Sparse Factorization.
Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians.
Surrogate Objectives for Batch Policy Optimization in One-step Decision Making.
PRNet: Self-Supervised Learning for Partial-to-Partial Registration.
Thompson Sampling and Approximate Inference.
Fisher Efficient Inference of Intractable Models.
Unlocking Fairness: a Trade-off Revisited.
Unsupervised State Representation Learning in Atari.
Recurrent Registration Neural Networks for Deformable Image Registration.
The Functional Neural Process.
Seeing the Wind: Visual Wind Speed Prediction with a Coupled Convolutional and Recurrent Neural Network.
Latent distance estimation for random geometric graphs.
Graph Agreement Models for Semi-Supervised Learning.
Private Learning Implies Online Learning: An Efficient Reduction.
Graph Structured Prediction Energy Networks.
Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models.
Finite-Sample Analysis for SARSA with Linear Function Approximation.
A Robust Non-Clairvoyant Dynamic Mechanism for Contextual Auctions.
Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural Networks.
A Little Is Enough: Circumventing Defenses For Distributed Learning.
A Communication Efficient Stochastic Multi-Block Alternating Direction Method of Multipliers.
Learning to Screen.
Self-Critical Reasoning for Robust Visual Question Answering.
Visualizing and Measuring the Geometry of BERT.
Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals.
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent.
Learning Deterministic Weighted Automata with Queries and Counterexamples.
Large Memory Layers with Product Keys.
From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction.
A Universally Optimal Multistage Accelerated Stochastic Gradient Method.
Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator.
Energy-Inspired Models: Learning with Sampler-Induced Distributions.
Facility Location Problem in Differential Privacy Model Revisited.
Characterizing the Exact Behaviors of Temporal Difference Learning Algorithms Using Markov Jump Linear System Theory.
N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules.
An adaptive Mirror-Prox method for variational inequalities with singular operators.
The Synthesis of XNOR Recurrent Neural Networks with Stochastic Logic.
Online Normalization for Training Neural Networks.
Distributed Low-rank Matrix Factorization With Exact Consensus.
Learning from Trajectories via Subgoal Discovery.
Multiclass Learning from Contradictions.
Robust and Communication-Efficient Collaborative Learning.
Gradient Dynamics of Shallow Univariate ReLU Networks.
The spiked matrix model with generative priors.
Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost.
Paradoxes in Fair Machine Learning.
Fast Convergence of Belief Propagation to Global Optima: Beyond Correlation Decay.
Certifiable Robustness to Graph Perturbations.
Fast and Accurate Least-Mean-Squares Solvers.
Learning to Infer Implicit Surfaces without 3D Supervision.
Learning-In-The-Loop Optimization: End-To-End Control And Co-Design Of Soft Robots Through Learned Deep Latent Representations.
Manipulating a Learning Defender and Ways to Counteract.
Modeling Dynamic Functional Connectivity with Latent Factor Gaussian Processes.
Fixing the train-test resolution discrepancy.
Average Individual Fairness: Algorithms, Generalization and Experiments.
Hyperbolic Graph Neural Networks.
Möbius Transformation for Fast Inner Product Search on Graph.
Spherical Text Embedding.
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model.
Fast Decomposable Submodular Function Minimization using Constrained Total Variation.
Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds.
Chirality Nets for Human Pose Regression.
Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning.
On Exact Computation with an Infinitely Wide Neural Net.
A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning.
Large-scale optimal transport map estimation using projection pursuit.
Learning Distributions Generated by One-Layer ReLU Networks.
Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices.
Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks.
Sparse Logistic Regression Learns All Discrete Pairwise Graphical Models.
Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle.
A Debiased MDI Feature Importance Measure for Random Forests.
Stability of Graph Scattering Transforms.
PyTorch: An Imperative Style, High-Performance Deep Learning Library.
Solving graph compression via optimal transport.
Provably Efficient Q-Learning with Low Switching Cost.
Learning Local Search Heuristics for Boolean Satisfiability.
Dynamic Local Regret for Non-convex Online Forecasting.
Differentially Private Anonymized Histograms.
Fast and Flexible Multi-Task Classification using Conditional Neural Adaptive Processes.
Post training 4-bit quantization of convolutional networks for rapid-deployment.
A Model to Search for Synthesizable Molecules.
Interaction Hard Thresholding: Consistent Sparse Quadratic Regression in Sub-quadratic Time and Space.
Solving Interpretable Kernel Dimensionality Reduction.
Modular Universal Reparameterization: Deep Multi-task Learning Across Diverse Domains.
Towards Understanding the Importance of Shortcut Connections in Residual Networks.
SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies.
A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment.
Detecting Overfitting via Adversarial Examples.
Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms.
Stein Variational Gradient Descent With Matrix-Valued Kernels.
Max-value Entropy Search for Multi-Objective Bayesian Optimization.
Re-examination of the Role of Latent Variables in Sequence Modeling.
Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks.
How degenerate is the parametrization of neural networks with the ReLU activation function?
LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition.
On two ways to use determinantal point processes for Monte Carlo integration.
The Implicit Bias of AdaGrad on Separable Data.
Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond.
A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening.
A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families.
Probabilistic Logic Neural Networks for Reasoning.
Sequence Modeling with Unconstrained Generation Order.
Bipartite expander Hopfield networks as self-decoding high-capacity error correcting codes.
Maximum Expected Hitting Cost of a Markov Decision Process and Informativeness of Rewards.
The Parameterized Complexity of Cascading Portfolio Scheduling.
Self-Routing Capsule Networks.
Continual Unsupervised Representation Learning.
Globally Convergent Newton Methods for Ill-conditioned Generalized Self-concordant Losses.
Competitive Gradient Descent.
MAVEN: Multi-Agent Variational Exploration.
PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments.
Coresets for Clustering with Fairness Constraints.
An adaptive nearest neighbor rule for classification.
Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules.
Constrained Reinforcement Learning Has Zero Duality Gap.
Nonlinear scaling of resource allocation in sensory bottlenecks.
Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization.
Phase Transitions and Cyclic Phenomena in Bandits with Switching Constraints.
Neural Spline Flows.
Lower Bounds on Adversarial Robustness from Optimal Transport.
Explicit Planning for Efficient Exploration in Reinforcement Learning.
Minimizers of the Empirical Risk and Risk Monotonicity.
What the Vec? Towards Probabilistically Grounded Embeddings.
Foundations of Comparison-Based Hierarchical Clustering.
On the Hardness of Robust Classification.
Learning elementary structures for 3D shape generation and matching.
List-decodable Linear Regression.
Implicit Regularization in Deep Matrix Factorization.
Learning-Based Low-Rank Approximations.
Estimating Convergence of Markov chains with L-Lag Couplings.
GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series.
Deep Scale-spaces: Equivariance Over Scale.
Trajectory of Alternating Direction Method of Multipliers and Adaptive Acceleration.
Normalization Helps Training of Quantized LSTM.
Modeling Tabular data using Conditional GAN.
Manifold-regression to predict from MEG/EEG brain signals without source modeling.
Nonzero-sum Adversarial Hypothesis Testing Games.
Localized Structured Prediction.
Multi-source Domain Adaptation for Semantic Segmentation.
Escaping from saddle points on Riemannian manifolds.
Optimal Sparse Decision Trees.
Emergence of Object Segmentation in Perturbed Generative Models.
Coresets for Archetypal Analysis.
Toward a Characterization of Loss Functions for Distribution Learning.
Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning.
Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning.
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization.
PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation.
Efficient and Thrifty Voting by Any Means Necessary.
Learning from Label Proportions with Generative Adversarial Networks.
Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction.
Tensor Monte Carlo: Particle Methods for the GPU era.
First Order Motion Model for Image Animation.
VIREL: A Variational Inference Framework for Reinforcement Learning.
On the Correctness and Sample Complexity of Inverse Reinforcement Learning.
Are sample means in multi-armed bandits positively or negatively biased?
Universal Invariant and Equivariant Graph Neural Networks.
Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input.
Approximate Bayesian Inference for a Mechanistic Model of Vesicle Release at a Ribbon Synapse.
Cross-lingual Language Model Pretraining.
Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs.
A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off.
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.
Graph-Based Semi-Supervised Learning with Non-ignorable Non-response.
Online Prediction of Switching Graph Labelings with Cluster Specialists.
GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs.
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup.
High-Quality Self-Supervised Deep Image Denoising.
Robust Principal Component Analysis with Adaptive Neighbors.
Infra-slow brain dynamics as a marker for cognitive function and decline.
On the convergence of single-call stochastic extra-gradient methods.
Efficient Smooth Non-Convex Stochastic Compositional Optimization via Stochastic Recursive Gradient Descent.
Subspace Detours: Building Transport Plans that are Optimal on Subspace Projections.
Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs.
Interior-Point Methods Strike Back: Solving the Wasserstein Barycenter Problem.
Likelihood-Free Overcomplete ICA and Applications In Causal Discovery.
Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks.
Differentiable Ranking and Sorting using Optimal Transport.
Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations.
Are Anchor Points Really Indispensable in Label-Noise Learning?
High-dimensional multivariate forecasting with low-rank Gaussian Copula Processes.
Discriminator optimal transport.
Hyperparameter Learning via Distributional Transfer.
Blow: a single-scale hyperconditioned flow for non-parallel raw-audio voice conversion.
Quantum Wasserstein Generative Adversarial Networks.
Discriminative Topic Modeling with Logistic LDA.
Learning Sparse Distributions using Iterative Hard Thresholding.
Precision-Recall Balanced Topic Modelling.
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds.
Hypothesis Set Stability and Generalization.
Learning Nonsymmetric Determinantal Point Processes.
Large Scale Structure of Neural Network Loss Landscapes.
Graph-based Discriminators: Sample Complexity and Expressiveness.
Interval timing in deep reinforcement learning agents.
On the Convergence Rate of Training Recurrent Neural Networks.
Fast AutoAugment.
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates.
DetNAS: Backbone Search for Object Detection.
Neural Shuffle-Exchange Networks - Sequence Processing in O(n log n) Time.
Multi-objects Generation with Amortized Structural Regularization.
Efficient Pure Exploration in Adaptive Round model.
On the Power and Limitations of Random Features for Understanding Neural Networks.
Weakly Supervised Instance Segmentation using the Bounding Box Tightness Prior.
Diffeomorphic Temporal Alignment Nets.
Code Generation as a Dual Task of Code Summarization.
BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling.
Nonstochastic Multiarmed Bandits with Unrestricted Delays.
Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders.
From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI.
Semi-supervisedly Co-embedding Attributed Networks.
Oblivious Sampling Algorithms for Private Data Analysis.
Maximum Mean Discrepancy Gradient Flow.
First-order methods almost always avoid saddle points: The case of vanishing step-sizes.
Grid Saliency for Context Explanations of Semantic Segmentation.
Domain Generalization via Model-Agnostic Learning of Semantic Features.
Wasserstein Weisfeiler-Lehman Graph Kernels.
Is Deeper Better only when Shallow is Good?
Single-Model Uncertainties for Deep Learning.
The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks.
Variational Bayesian Decision-making for Continuous Utilities.
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks.
Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation.
Bayesian Batch Active Learning as Sparse Subset Approximation.
Bayesian Learning of Sum-Product Networks.
Copula Multi-label Learning.
Reliable training and estimation of variance networks.
Neural Machine Translation with Soft Prototype.
Singleshot : a scalable Tucker tensor decomposition.
Anti-efficient encoding in emergent communication.
Learning to Perform Local Rewriting for Combinatorial Optimization.
Meta-Surrogate Benchmarking for Hyperparameter Optimization.
UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization.
Progressive Augmentation of GANs.
Convergence Guarantees for Adaptive Bayesian Quadrature Methods.
L_DMI: A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise.
Distributional Reward Decomposition for Reinforcement Learning.
Direct Optimization through arg max for Discrete Variational Auto-Encoder.
Fully Parameterized Quantile Function for Distributional Reinforcement Learning.
Deep Model Transferability from Attribution Maps.
Mining GOLD Samples for Conditional GANs.
Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers.
Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning.
Compositional De-Attention Networks.
Towards a Zero-One Law for Column Subset Selection.
Intrinsic dimension of data representations in deep neural networks.
Divergence-Augmented Policy Optimization.
Dynamic Ensemble Modeling Approach to Nonstationary Neural Decoding in Brain-Computer Interfaces.
Iterative Least Trimmed Squares for Mixed Linear Regression.
Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection.
Constrained deep neural network architecture search for IoT devices accounting for hardware calibration.
Learning from Bad Data via Generation.
Comparing Unsupervised Word Translation Methods Step by Step.
Learning Dynamics of Attention: Human Prior for Interpretable Machine Reasoning.
DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters.
AutoAssist: A Framework to Accelerate Training of Deep Neural Networks.
Efficiently escaping saddle points on manifolds.
Deep Active Learning with a Neural Architecture Search.
Effective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network.
Scalable inference of topic evolution via models for latent geometric structures.
A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning.
Equipping Experts/Bandits with Long-term Memory.
Adaptive Gradient-Based Meta-Learning Methods.
Learning by Abstraction: The Neural State Machine.
MaCow: Masked Convolutional Generative Flow.
DM2C: Deep Mixed-Modal Clustering.
Doubly-Robust Lasso Bandit.
Adversarial Training and Robustness for Multiple Perturbations.
Generalized Block-Diagonal Structure Pursuit: Learning Soft Latent Task Assignment against Negative Transfer.
Abstract Reasoning with Distracting Features.
Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs.
AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification.
Co-Generation with GANs using AIS based HMC.
Learning GANs and Ensembles Using Discrepancy.
Variance Reduced Policy Evaluation with Smooth Function Approximation.
Comparison Against Task Driven Artificial Neural Networks Reveals Functional Properties in Mouse Visual Cortex.
XLNet: Generalized Autoregressive Pretraining for Language Understanding.
Acceleration via Symplectic Discretization of High-Resolution Differential Equations.
In-Place Zero-Space Memory Protection for CNN.
Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels.
Learning Disentangled Representations for Recommendation.
Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently.
A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning.
Online Markov Decoding: Lower Bounds and Near-Optimal Approximation Algorithms.
Connective Cognition Network for Directional Visual Commonsense Reasoning.
Topology-Preserving Deep Image Segmentation.
A Latent Variational Framework for Stochastic Optimization.
Invertible Convolutional Flow.
Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model.
Limiting Extrapolation in Linear Approximate Value Iteration.
Optimal Best Markovian Arm Identification with Fixed Confidence.
Quantum Embedding of Knowledge for Reasoning.
Focused Quantization for Sparse CNNs.
Adaptive Influence Maximization with Myopic Feedback.
An Adaptive Empirical Bayesian Method for Sparse Deep Learning.
Exploring Unexplored Tensor Network Decompositions for Convolutional Neural Networks.
Robustness to Adversarial Perturbations in Learning from Incomplete Data.
A Refined Margin Distribution Analysis for Forest Representation Learning.
Ouroboros: On Accelerating Training of Transformer-Based Language Models.
Time-series Generative Adversarial Networks.
Scalable Global Optimization via Local Bayesian Optimization.
A Step Toward Quantifying Independently Reproducible Machine Learning Research.
Markov Random Fields for Collaborative Filtering.
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model.
Regularized Gradient Boosting.
Off-Policy Evaluation via Off-Policy Classification.
Policy Learning for Fairness in Ranking.
Optimal Stochastic and Online Learning with Individual Iterates.
Characterizing Bias in Classifiers using Generative Models.
Reducing the variance in online optimization by transporting past gradients.
Learning to Predict Without Looking Ahead: World Models Without Forward Prediction.
Weight Agnostic Neural Networks.
Adaptive Sequence Submodularity.
Input Similarity from the Neural Network Perspective.
Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion.
Latent Ordinary Differential Equations for Irregularly-Sampled Time Series.
Balancing Efficiency and Fairness in On-Demand Ridesourcing.
Learning Disentangled Representation for Robust Person Re-identification.
On Testing for Biases in Peer Review.
Incremental Few-Shot Learning with Attention Attractor Networks.
Face Reconstruction from Voice using Generative Adversarial Networks.
On the Accuracy of Influence Functions for Measuring Group Effects.
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting.
Learning Non-Convergent Non-Persistent Short-Run MCMC Toward Energy-Based Model.
Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions.
Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness.
Learning in Generalized Linear Contextual Bandits with Stochastic Delays.
Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium.
On the Utility of Learning about Humans for Human-AI Coordination.
Estimating Entropy of Distributions in Constant Space.
ANODEV2: A Coupled Neural ODE Framework.
E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings.
Data-driven Estimation of Sinusoid Frequencies.
Mutually Regressive Point Processes.
Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery.
On the number of variables to use in principal component regression.
PHYRE: A New Benchmark for Physical Reasoning.
Fast Parallel Algorithms for Statistical Subset Selection Problems.
Multivariate Triangular Quantile Maps for Novelty Detection.
MixMatch: A Holistic Approach to Semi-Supervised Learning.
Ordered Memory.
Neural Similarity Learning.
Few-shot Video-to-Video Synthesis.
Visual Concept-Metaconcept Learning.
Deep imitation learning for molecular inverse problems.
SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers.
Learning Mean-Field Games.
Fair Algorithms for Clustering.
Breaking the Glass Ceiling for Embedding-Based Classifiers for Large Output Spaces.
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers.
Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees.
Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers.
Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks.
Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs.
Cost Effective Active Search.
Hyperbolic Graph Convolutional Neural Networks.
Spectral Modification of Graphs for Improved Spectral Clustering.
Adaptive Cross-Modal Few-shot Learning.
Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting.
Policy Evaluation with Latent Confounders via Optimal Balance.
On Single Source Robustness in Deep Fusion Models.
Prior-Free Dynamic Auctions with Low Regret Buyers.
Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities.
Blocking Bandits.
Adaptive Auxiliary Task Weighting for Reinforcement Learning.
The Convergence Rate of Neural Networks for Learned Functions of Different Frequencies.
Distribution-Independent PAC Learning of Halfspaces with Massart Noise.
Optimal Sketching for Kronecker Product Regression and Low Rank Approximation.
Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference.
Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks.
Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning.
When does label smoothing help?
Game Design for Eliciting Distinguishable Behavior.
End to end learning and optimization on graphs.
A state-space model for inferring effective connectivity of latent neural dynamics from simultaneous EEG/fMRI.
Unsupervised Scalable Representation Learning for Multivariate Time Series.
Making the Cut: A Bandit-based Approach to Tiered Interviewing.
Offline Contextual Bayesian Optimization.
Fast Efficient Hyperparameter Tuning for Policy Gradient Methods.
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments.
Kernel Instrumental Variable Regression.
Scalable Bayesian dynamic covariance modeling with variational Wishart and inverse Wishart processes.
Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations.
Learning low-dimensional state embeddings and metastable clusters from time series data.
Efficient Deep Approximation of GMMs.
Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem.
Decentralized Cooperative Stochastic Bandits.
Partially Encrypted Deep Learning using Functional Encryption.
Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning.
Disentangling Influence: Using disentangled representations to audit model predictions.
State Aggregation Learning from Markov Transition Data.
No-Press Diplomacy: Modeling Multi-Agent Gameplay.
Multi-relational Poincaré Graph Embeddings.
Globally optimal score-based learning of directed acyclic graphs in high-dimensions.
Double Quantization for Communication-Efficient Distributed Optimization.
Massively scalable Sinkhorn distances via the Nyström method.
U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging.
LIIR: Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning.
Uncertainty-based Continual Learning with Adaptive Regularization.
Understanding and Improving Layer Normalization.
Learning New Tricks From Old Dogs: Multi-Source Transfer Learning From Pre-Trained Networks.
A Geometric Perspective on Optimal Representations for Reinforcement Learning.
On Adversarial Mixup Resynthesis.
Propagating Uncertainty in Reinforcement Learning via Wasserstein Barycenters.
Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate.
Pseudo-Extended Markov chain Monte Carlo.
Training Language GANs from Scratch.
Practical Deep Learning with Bayesian Principles.
Learning Deep Bilinear Transformation for Fine-grained Image Representation.
Beyond Alternating Updates for Matrix Factorization with Inertial Bregman Proximal Gradient Algorithms.
Efficient Graph Generation with Graph Recurrent Attention Networks.
Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections.
Embedding Symbolic Knowledge into Deep Networks.
Curvilinear Distance Metric Learning.
Data Cleansing for Models Trained with SGD.
Understanding Attention and Generalization in Graph Neural Networks.
Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models.
Learning dynamic polynomial proofs.
Flow-based Image-to-Image Translation with Feature Disentanglement.
Limitations of the empirical Fisher approximation for natural gradient descent.
Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints.
q-means: A quantum algorithm for unsupervised machine learning.
Full-Gradient Representation for Neural Network Visualization.
Differentially Private Markov Chain Monte Carlo.
A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models.
Thinning for Accelerating the Learning of Point Processes.
Approximation Ratios of Graph Neural Networks for Combinatorial Problems.
Practical and Consistent Estimation of f-Divergences.
Regularized Weighted Low Rank Approximation.
Teaching Multiple Concepts to a Forgetful Learner.
Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs.
SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models.
A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution.
Cross Attention Network for Few-shot Classification.
Uncoupled Regression from Pairwise Comparison Data.
Learning Generalizable Device Placement Algorithms for Distributed Machine Learning.
Joint Optimization of Tree-based Index and Deep Model for Recommender Systems.
Handling correlated and repeated measurements with the smoothed multivariate square-root Lasso.
PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph.
A First-Order Algorithmic Framework for Distributionally Robust Logistic Regression.
Improved Precision and Recall Metric for Assessing Generative Models.
MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable Quantization.
Domes to Drones: Self-Supervised Active Triangulation for 3D Human Pose Reconstruction.
iSplit LBI: Individualized Partial Ranking with Ties via Split LBI.
Exact Rate-Distortion in Autoencoders via Echo Noise.
Compression with Flows via Local Bits-Back Coding.
Principal Component Projection and Regression in Nearly Linear Time through Asymmetric SVRG.
Cross-sectional Learning of Extremal Dependence among Financial Assets.
Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling.
Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction.
Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks.
Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction.
A Normative Theory for Causal Inference and Bayes Factor Computation in Neural Circuits.
Verified Uncertainty Calibration.
Learning Representations for Time Series Clustering.
Efficiently Estimating Erdos-Renyi Graphs with Node Differential Privacy.
Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation.
Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data.
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates.
Bat-G net: Bat-inspired High-Resolution 3D Image Reconstruction using Ultrasonic Echoes.
Coda: An End-to-End Neural Program Decompiler.
Exact inference in structured prediction.
MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies.
Asymptotics for Sketching in Least Squares Regression.
Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD.
Ultra Fast Medoid Identification via Correlated Sequential Halving.
Adaptive GNN for Image Analysis and Editing.
Predicting the Politics of an Image Using Webly Supervised Data.
LCA: Loss Change Allocation for Neural Network Training.
Implicit Generation and Modeling with Energy Based Models.
Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask.
Dancing to Music.
Learning Sample-Specific Models with Low-Rank Personalized Regression.
Deep Generalized Method of Moments for Instrumental Variable Analysis.
Thompson Sampling with Information Relaxation Penalties.
Conformalized Quantile Regression.
Practical Differentially Private Top-k Selection with Pay-what-you-get Composition.
Making AI Forget You: Data Deletion in Machine Learning.
The Landscape of Non-convex Empirical Risk with Degenerate Population Risk.
SGD on Neural Networks Learns Functions of Increasing Complexity.
Universal Boosting Variational Inference.
Capacity Bounded Differential Privacy.
First order expansion of convex regularized estimators.
HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models.
The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the XAUC Metric.
Assessing Disparate Impact of Personalized Interventions: Identifiability and Bounds.
Arbicon-Net: Arbitrary Continuous Geometric Transformation Networks for Image Registration.
PC-Fairness: A Unified Framework for Measuring Causality-based Fairness.
Kernel-Based Approaches for Sequence Modeling: Connections to Neural Methods.
Implicitly learning to reason in first-order logic.
Communication-Efficient Distributed Learning via Lazily Aggregated Quantized Gradients.
Adversarial training for free!
Transfusion: Understanding Transfer Learning for Medical Imaging.
KerGM: Kernelized Graph Matching.
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning.
Meta-Curvature.
Optimal Decision Tree with Noisy Outcomes.
Inherent Weight Normalization in Stochastic Neural Networks.
A Flexible Generative Framework for Graph-based Semi-supervised Learning.
SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems.
Fully Dynamic Consistent Facility Location.
Neural Lyapunov Control.
Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control.
DppNet: Approximating Determinantal Point Processes with Deep Networks.
Deep Set Prediction Networks.
Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks.
Distinguishing Distributions When Samples Are Strategically Transformed.
Ultrametric Fitting by Gradient Descent.
FastSpeech: Fast, Robust and Controllable Text to Speech.
Backpropagation-Friendly Eigendecomposition.
Thompson Sampling for Multinomial Logit Contextual Bandits.
Augmented Neural ODEs.
Convergent Policy Optimization for Safe Reinforcement Learning.
Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits.
Deep Signature Transforms.
Approximate Inference Turns Deep Networks into Gaussian Processes.
Robust Multi-agent Counterfactual Prediction.
Real-Time Reinforcement Learning.
Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition.
Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching.
Putting An End to End-to-End: Gradient-Isolated Learning of Representations.
Learning Temporal Pose Estimation from Sparsely-Labeled Videos.
Fast Structured Decoding for Sequence Models.
Spatially Aggregated Gaussian Processes with Multivariate Areal Outputs.
Multi-mapping Image-to-Image Translation via Learning Disentanglement.
Locally Private Gaussian Estimation.
Implicit Regularization for Optimal Sparse Recovery.
Copula-like Variational Inference.
Quality Aware Generative Adversarial Networks.
On Lazy Training in Differentiable Programming.
Fooling Neural Network Interpretations via Adversarial Model Manipulation.
Combinatorial Bayesian Optimization using the Graph Cartesian Product.
Addressing Failure Prediction by Learning Model Confidence.
Safe Exploration for Interactive Machine Learning.
Epsilon-Best-Arm Identification in Pay-Per-Reward Multi-Armed Bandits.
Learning Hierarchical Priors in VAEs.
Regularizing Trajectory Optimization with Denoising Autoencoders.
A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization.
On the Global Convergence of (Fast) Incremental Expectation Maximization Methods.
Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function.
Bridging Machine Learning and Logical Reasoning by Abductive Learning.
Identifying Causal Effects via Context-specific Independence Relations.
Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components.
Probabilistic Watershed: Sampling all spanning forests for seeded segmentation and semi-supervised learning.
Heterogeneous Graph Learning for Visual Commonsense Reasoning.
Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels.
Glyce: Glyph-vectors for Chinese Character Representations.
Quaternion Knowledge Graph Embeddings.
One-Shot Object Detection with Co-Attention and Co-Excitation.
PAC-Bayes under potentially heavy tails.
Knowledge Extraction with No Observable Data.
On the Optimality of Perturbations in Stochastic and Adversarial Multi-armed Bandit Problems.
Discovering Neural Wirings.
Dual Variational Generation for Low Shot Heterogeneous Face Recognition.
Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries.
On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective.
Non-asymptotic Analysis of Stochastic Methods for Non-Smooth Non-Convex Regularized Problems.
Learning Robust Options by Conditional Value at Risk Optimization.
Stagewise Training Accelerates Convergence of Testing Error Over SGD.
Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller.
On the Calibration of Multiclass Classification with Rejection.
Direct Estimation of Differential Functional Graphical Models.
Positive-Unlabeled Compression on the Cloud.
Asymmetric Valleys: Beyond Sharp and Flat Local Minima.
Optimal Analysis of Subset-Selection Based L_p Low-Rank Approximation.
Conformal Prediction Under Covariate Shift.
Learning Transferable Graph Exploration.
Adapting Neural Networks for the Estimation of Treatment Effects.
Park: An Open Platform for Learning-Augmented Computer Systems.
Total Least Squares Regression in Input Sparsity Time.
Transfer Anomaly Detection by Inferring Latent Domain Representations.
Information-Theoretic Confidence Bounds for Reinforcement Learning.
Deep Structured Prediction for Facial Landmark Detection.
Training Image Estimators without Image Ground Truth.
Backprop with Approximate Activations for Memory-efficient Network Training.
Minimax Optimal Estimation of Approximate Differential Privacy on Neighboring Databases.
SpiderBoost and Momentum: Faster Variance Reduction Algorithms.
Gradient Information for Representation and Modeling.
Initialization of ReLUs for Dynamical Isometry.
Interlaced Greedy Algorithm for Maximization of Submodular Functions in Nearly Linear Time.
Semi-Parametric Dynamic Contextual Pricing.
Multiview Aggregation for Learning Category-Specific Shape Reconstruction.
Large Scale Markov Decision Processes with Changing Rewards.
Hyper-Graph-Network Decoders for Block Codes.
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections.
Perceiving the arrow of time in autoregressive motion.
Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity.
Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Learning.
Rethinking the CSC Model for Natural Images.
More Is Less: Learning Efficient Video Representations by Big-Little Network and Depthwise Temporal Aggregation.
Disentangled behavioural representations.
Kernel Stein Tests for Multiple Model Comparison.
A Tensorized Transformer for Language Modeling.
Partitioning Structure Learning for Segmented Linear Regression Trees.
Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function.
Conditional Independence Testing using Generative Adversarial Networks.
GENO - GENeric Optimization for Classical Machine Learning.
Information Competing Process for Learning Diversified Representations.
Order Optimal One-Shot Distributed Learning.
Provably Powerful Graph Networks.
Discrimination in Online Markets: Effects of Social Bias on Learning from Reviews and Policy Design.
Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks.
Fully Neural Network based Model for General Temporal Point Processes.
Sample-Efficient Deep Reinforcement Learning via Episodic Backward Update.
The Randomized Midpoint Method for Log-Concave Sampling.
Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach.
Improving Textual Network Learning with Variational Homophilic Embeddings.
Controllable Text-to-Image Generation.
An Improved Analysis of Training Over-parameterized Deep Neural Networks.
Blended Matching Pursuit.
Controlling Neural Level Sets.
Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models.
DAC: The Double Actor-Critic Architecture for Learning Options.
Generalized Off-Policy Actor-Critic.
CNN2: Viewpoint Generalization via a Binocular Vision.
XNAS: Neural Architecture Search with Expert Advice.
Random deep neural networks are biased towards simple functions.
Transferable Normalization: Towards Improving Transferability of Deep Neural Networks.
Mapping State Space using Landmarks for Universal Goal Reaching.
Variational Structured Semantic Inference for Diverse Image Captioning.
Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting.
Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning.
Neural networks grown and self-organized by noise.
Channel Gating Neural Networks.
Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization.
Nonconvex Low-Rank Tensor Completion from Noisy Data.
The Cells Out of Sample (COOS) dataset and benchmarks for measuring out-of-sample generalization of image classifiers.
Visualizing the PHATE of Neural Networks.
Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training.
Meta-Learning Representations for Continual Learning.
The Label Complexity of Active Learning from Observational Data.
Importance Resampling for Off-policy Prediction.
Better Exploration with Optimistic Actor Critic.
Multi-marginal Wasserstein GAN.
On the Curved Geometry of Accelerated Optimization.
On the Ineffectiveness of Variance Reduced Optimization for Deep Learning.
Cascaded Dilated Dense Network with Two-step Data Consistency for MRI Reconstruction.
Coordinated hippocampal-entorhinal replay as structural inference.
Data-Dependence of Plateau Phenomenon in Learning with Neural Network - Statistical Mechanical Analysis.
Learnable Tree Filter for Structure-preserving Feature Transform.
Fast Sparse Group Lasso.
Variational Denoising Network: Toward Blind Noise Modeling and Removal.
Self-Supervised Generalisation with Meta Auxiliary Learning.
Incremental Scene Synthesis.
ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuracies.
Quadratic Video Interpolation.
A New Defense Against Adversarial Images: Turning a Weakness into a Strength.
Positional Normalization.
Multivariate Sparse Coding of Nonstationary Covariances with Gaussian Processes.
Hierarchical Optimal Transport for Document Representation.
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs.
Strategizing against No-regret Learners.
Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss.
Guided Similarity Separation for Image Retrieval.
Unconstrained Monotonic Neural Networks.
Efficient Meta Learning via Minibatch Proximal Update.
SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points.
HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs.
Expressive power of tensor-network factorizations for probabilistic modeling.
Hyperspherical Prototype Networks.
Fixing Implicit Derivatives: Trust-Region Based Learning of Continuous Energy Functions.
Extending Stein's unbiased risk estimator to train deep denoisers with correlated pairs of noisy images.
Fine-grained Optimization of Deep Neural Networks.
Neural Diffusion Distance for Image Segmentation.
Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution.
Multi-View Reinforcement Learning.
Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards.
Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift.
Computing Full Conformal Prediction Set with Approximate Homotopy.
Deliberative Explanations: visualizing network insecurities.
Sampling Sketches for Concave Sublinear Functions of Frequencies.
Distributional Policy Optimization: An Alternative Approach for Continuous Control.
Conditional Structure Generation through Graph Variational Generative Adversarial Nets.
Twin Auxilary Classifiers GAN.
Regression Planning Networks.
CondConv: Conditionally Parameterized Convolutions for Efficient Inference.
Cross-channel Communication Networks.
Model Compression with Adversarial Robustness: A Unified Optimization Framework.
Image Synthesis with a Single (Robust) Classifier.
Finding Friend and Foe in Multi-Agent Games.
Envy-Free Classification.
Online sampling from log-concave distributions.
Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up.
On The Classification-Distortion-Perception Tradeoff.
Convolution with even-sized kernels and symmetric padding.
Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning.
Combinatorial Inference against Label Noise.
A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation.
Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs.
Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence.
Reconciling λ-Returns with Experience Replay.
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations.
Deep Supervised Summarization: Algorithm and Application to Learning Instructions.
Region-specific Diffeomorphic Metric Mapping.
Selecting the independent coordinates of manifolds with large aspect ratios.
Learning Perceptual Inference by Contrasting.
Nonparametric Regressive Point Processes Based on Conditional Gaussian Processes.
Secretary Ranking with Minimal Inversions.
Learning to Propagate for Graph Meta-Learning.
Polynomial Cost of Adaptation for X-Armed Bandits.
Explicit Disentanglement of Appearance and Perspective in Generative Models.
A Condition Number for Joint Optimization of Cycle-Consistent Networks.
General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme.
Combinatorial Bandits with Relative Feedback.
Deep Learning without Weight Transport.
Point-Voxel CNN for Efficient 3D Deep Learning.
An Accelerated Decentralized Stochastic Proximal Algorithm for Finite Sums.
Optimal Pricing in Repeated Posted-Price Auctions with Different Patience of the Seller and the Buyer.
Powerset Convolutional Neural Networks.
Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels.
Multi-label Co-regularization for Semi-supervised Facial Action Unit Recognition.
Memory-oriented Decoder for Light Field Salient Object Detection.
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge.
DATA: Differentiable ArchiTecture Approximation.
NeurVPS: Neural Vanishing Point Scanning via Conic Convolution.
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition.
RUBi: Reducing Unimodal Biases for Visual Question Answering.
Efficient Symmetric Norm Regression via Linear Sketching.
Fast Low-rank Metric Learning for Large-scale and High-dimensional Data.
Learning Conditional Deformable Templates with Convolutional Networks.
Volumetric Correspondence Networks for Optical Flow.
Poisson-Randomized Gamma Dynamical Systems.
Differentiable Cloth Simulation for Inverse Problems.
Network Pruning via Transformable Architecture Search.
Selecting Optimal Decisions via Distributionally Robust Nearest-Neighbor Regression.
NAT: Neural Architecture Transformer for Accurate and Compact Architectures.
Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives.
Multiway clustering via tensor block models.
Saccader: Improving Accuracy of Hard Attention Models for Vision.
Deep Equilibrium Models.
No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms.
ETNet: Error Transition Network for Arbitrary Style Transfer.
Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control.
Towards closing the gap between the theory and practice of SVRG.
Adversarial Self-Defense for Cycle-Consistent GANs.
Trust Region-Guided Proximal Policy Optimization.
RSN: Randomized Subspace Newton.
Importance Weighted Hierarchical Variational Inference.
SySCD: A System-Aware Parallel Coordinate Descent Algorithm.
Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling.
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis.
CPM-Nets: Cross Partial Multi-View Networks.
AGEM: Solving Linear Inverse Problems via Deep Priors and Sampling.
Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos.
Differentially Private Bayesian Linear Regression.
vGraph: A Generative Model for Joint Community Detection and Node Representation Learning.
Batched Multi-armed Bandits Problem.
DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction.
Metric Learning for Adversarial Robustness.
Zero-Shot Semantic Segmentation.
Equitable Stable Matchings in Quadratic Time.
Invert to Learn to Invert.
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation.
muSSP: Efficient Min-cost Flow Algorithm for Multi-object Tracking.
A Primal-Dual link between GANs and Autoencoders.
Learning Erdos-Renyi Random Graphs via Edge Detecting Queries.
Reducing Noise in GAN Training with Variance Reduced Extragradient.
Block Coordinate Regularization by Denoising.
Chasing Ghosts: Instruction Following as Bayesian State Tracking.
Deep ReLU Networks Have Surprisingly Few Activation Patterns.
Experience Replay for Continual Learning.
Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation.
Provable Gradient Variance Guarantees for Black-Box Variational Inference.
Joint-task Self-supervised Learning for Temporal Correspondence.
Generalization in Generative Adversarial Networks: A Novel Perspective from Privacy Protection.
Noise-tolerant fair classification.
Blind Super-Resolution Kernel Estimation using an Internal-GAN.
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise.
Generalized Sliced Wasserstein Distances.
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance.
Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement.
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle.
The Point Where Reality Meets Fantasy: Mixed Adversarial Generators for Image Splice Detection.
DeepUSPS: Deep Robust Unsupervised Saliency Prediction via Self-supervision.
Multi-Resolution Weak Supervision for Sequential Data.
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation.
Differentially Private Algorithms for Learning Mixtures of Separated Gaussians.
Private Hypothesis Selection.
FreeAnchor: Learning to Match Anchors for Visual Object Detection.
Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks.
Adversarial Examples Are Not Bugs, They Are Features.
Meta-Learning with Implicit Gradients.
GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism.
Unsupervised learning of object structure and dynamics from videos.
High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks.
Stand-Alone Self-Attention in Vision Models.
Ask not what AI can do, but what AI should do: Towards a framework of task delegability.
Zero-shot Learning via Simultaneous Generating and Learning.
Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video.
Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers.
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks.
Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation.
