NeurIPS(NIPS) 2016 论文列表
Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain.
|
Only H is left: Near-tight Episodic PAC RL.
Learning to Poke by Poking: Experiential Learning of Intuitive Physics.
Cyclades: Conflict-free Asynchronous Machine Learning.
Learning Deep Parsimonious Representations.
An Online Sequence-to-Sequence Model Using Partial Conditioning.
Fundamental Limits of Budget-Fidelity Trade-off in Label Crowdsourcing.
A primal-dual method for conic constrained distributed optimization problems.
Disentangling factors of variation in deep representation using adversarial training.
Optimal Binary Classifier Aggregation for General Losses.
Dual Decomposed Learning with Factorwise Oracle for Structural SVM of Large Output Domain.
Gaussian Processes for Survival Analysis.
Poisson-Gamma dynamical systems.
Unsupervised Learning of 3D Structure from Images.
Recovery Guarantee of Non-negative Matrix Factorization via Alternating Updates.
SDP Relaxation with Randomized Rounding for Energy Disaggregation.
Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities.
Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes.
A Bayesian method for reducing bias in neural representational similarity analysis.
A posteriori error bounds for joint matrix decomposition problems.
Beyond Exchangeability: The Chinese Voting Process.
Normalized Spectral Map Synchronization.
k*-Nearest Neighbors: From Global to Local.
Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods.
Understanding the Effective Receptive Field in Deep Convolutional Neural Networks.
Threshold Bandits, With and Without Censored Feedback.
Full-Capacity Unitary Recurrent Neural Networks.
Exploiting Tradeoffs for Exact Recovery in Heterogeneous Stochastic Block Models.
Supervised Word Mover's Distance.
Near-Optimal Smoothing of Structured Conditional Probability Matrices.
Achieving budget-optimality with adaptive schemes in crowdsourcing.
Feature selection in functional data classification with recursive maxima hunting.
An Architecture for Deep, Hierarchical Generative Models.
Structure-Blind Signal Recovery.
Multi-step learning and underlying structure in statistical models.
Supervised Learning with Tensor Networks.
Conditional Image Generation with PixelCNN Decoders.
Optimal Architectures in a Solvable Model of Deep Networks.
Neural Universal Discrete Denoiser.
Kernel Bayesian Inference with Posterior Regularization.
Unified Methods for Exploiting Piecewise Linear Structure in Convex Optimization.
Algorithms and matching lower bounds for approximately-convex optimization.
Improving Variational Autoencoders with Inverse Autoregressive Flow.
Learning in Games: Robustness of Fast Convergence.
Multistage Campaigning in Social Networks.
Disease Trajectory Maps.
Assortment Optimization Under the Mallows model.
Iterative Refinement of the Approximate Posterior for Directed Belief Networks.
Asynchronous Parallel Greedy Coordinate Descent.
Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning.
Learning Parametric Sparse Models for Image Super-Resolution.
Visual Question Answering with Question Representation Update (QRU).
Bayesian Intermittent Demand Forecasting for Large Inventories.
Efficient High-Order Interaction-Aware Feature Selection Based on Conditional Mutual Information.
Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods.
Efficient Neural Codes under Metabolic Constraints.
Learning brain regions via large-scale online structured sparse dictionary learning.
Professor Forcing: A New Algorithm for Training Recurrent Networks.
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds.
Dual Space Gradient Descent for Online Learning.
Latent Attention For If-Then Program Synthesis.
Generative Adversarial Imitation Learning.
Optimal Learning for Multi-pass Stochastic Gradient Methods.
Coevolutionary Latent Feature Processes for Continuous-Time User-Item Interactions.
Computing and maximizing influence in linear threshold and triggering models.
Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics.
Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent.
Efficient state-space modularization for planning: theory, behavioral and neural signatures.
Interaction Networks for Learning about Objects, Relations and Physics.
An Efficient Streaming Algorithm for the Submodular Cover Problem.
Tagger: Deep Unsupervised Perceptual Grouping.
More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning.
Ancestral Causal Inference.
Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning.
Fast and accurate spike sorting of high-channel count probes with KiloSort.
Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction.
An urn model for majority voting in classification ensembles.
Clustering Signed Networks with the Geometric Mean of Laplacians.
A Consistent Regularization Approach for Structured Prediction.
Incremental Variational Sparse Gaussian Process Regression.
Fast recovery from a union of subspaces.
LightRNN: Memory and Computation-Efficient Recurrent Neural Networks.
Backprop KF: Learning Discriminative Deterministic State Estimators.
Learning Additive Exponential Family Graphical Models via \ell_{2, 1}-norm Regularized M-Estimation.
beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data.
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings.
Maximal Sparsity with Deep Networks?
Using Fast Weights to Attend to the Recent Past.
Stochastic Three-Composite Convex Minimization.
Probabilistic Linear Multistep Methods.
Safe Exploration in Finite Markov Decision Processes with Gaussian Processes.
Adaptive Smoothed Online Multi-Task Learning.
Learning values across many orders of magnitude.
Neurons Equipped with Intrinsic Plasticity Learn Stimulus Intensity Statistics.
Sparse Support Recovery with Non-smooth Loss Functions.
Completely random measures for modelling block-structured sparse networks.
A Locally Adaptive Normal Distribution.
Edge-exchangeable graphs and sparsity.
A Minimax Approach to Supervised Learning.
Linear Feature Encoding for Reinforcement Learning.
Protein contact prediction from amino acid co-evolution using convolutional networks for graph-valued images.
Batched Gaussian Process Bandit Optimization via Determinantal Point Processes.
Mapping Estimation for Discrete Optimal Transport.
Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling.
Spectral Learning of Dynamic Systems from Nonequilibrium Data.
Learning Deep Embeddings with Histogram Loss.
One-vs-Each Approximation to Softmax for Scalable Estimation of Probabilities.
Fast Algorithms for Robust PCA via Gradient Descent.
Learnable Visual Markers.
Bayesian Optimization with Robust Bayesian Neural Networks.
Memory-Efficient Backpropagation Through Time.
Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences.
Binarized Neural Networks.
Linear Relaxations for Finding Diverse Elements in Metric Spaces.
Agnostic Estimation for Misspecified Phase Retrieval Models.
Coresets for Scalable Bayesian Logistic Regression.
A Sparse Interactive Model for Matrix Completion with Side Information.
Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy.
Convolutional Neural Fabrics.
Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages.
A Multi-step Inertial Forward-Backward Splitting Method for Non-convex Optimization.
Deep Exploration via Bootstrapped DQN.
The Power of Optimization from Samples.
Guided Policy Search via Approximate Mirror Descent.
Quantum Perceptron Models.
Kernel Observers: Systems-Theoretic Modeling and Inference of Spatiotemporally Evolving Processes.
Learning to learn by gradient descent by gradient descent.
Tracking the Best Expert in Non-stationary Stochastic Environments.
Data driven estimation of Laplace-Beltrami operator.
Mistake Bounds for Binary Matrix Completion.
Greedy Feature Construction.
Tractable Operations for Arithmetic Circuits of Probabilistic Models.
Select-and-Sample for Spike-and-Slab Sparse Coding.
Spatio-Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments.
Cooperative Inverse Reinforcement Learning.
Infinite Hidden Semi-Markov Modulated Interaction Point Process.
Improving PAC Exploration Using the Median Of Means.
Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences.
Global Optimality of Local Search for Low Rank Matrix Recovery.
Online Pricing with Strategic and Patient Buyers.
Large-Scale Price Optimization via Network Flow.
CliqueCNN: Deep Unsupervised Exemplar Learning.
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering.
A forward model at Purkinje cell synapses facilitates cerebellar anticipatory control.
Average-case hardness of RIP certification.
Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale.
Learning Sparse Gaussian Graphical Models with Overlapping Blocks.
The Product Cut.
Minimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning.
Can Active Memory Replace Attention?
Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA.
Threshold Learning for Optimal Decision Making.
The Multiple Quantile Graphical Model.
Ladder Variational Autoencoders.
Probing the Compositionality of Intuitive Functions.
Communication-Optimal Distributed Clustering.
Wasserstein Training of Restricted Boltzmann Machines.
The Forget-me-not Process.
Joint quantile regression in vector-valued RKHSs.
High Dimensional Structured Superposition Models.
Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation.
MetaGrad: Multiple Learning Rates in Online Learning.
Unsupervised Risk Estimation Using Only Conditional Independence Structure.
Graphical Time Warping for Joint Alignment of Multiple Curves.
Tight Complexity Bounds for Optimizing Composite Objectives.
Matching Networks for One Shot Learning.
Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes.
Lifelong Learning with Weighted Majority Votes.
Estimating Nonlinear Neural Response Functions using GP Priors and Kronecker Methods.
Fast Distributed Submodular Cover: Public-Private Data Summarization.
Dynamic matrix recovery from incomplete observations under an exact low-rank constraint.
Generalization of ERM in Stochastic Convex Optimization: The Dimension Strikes Back.
Data Programming: Creating Large Training Sets, Quickly.
Exact Recovery of Hard Thresholding Pursuit.
Towards Conceptual Compression.
Dimension-Free Iteration Complexity of Finite Sum Optimization Problems.
Online and Differentially-Private Tensor Decomposition.
Community Detection on Evolving Graphs.
Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers.
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism.
The Limits of Learning with Missing Data.
Strategic Attentive Writer for Learning Macro-Actions.
Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations.
Spatiotemporal Residual Networks for Video Action Recognition.
Reconstructing Parameters of Spreading Models from Partial Observations.
Linear Contextual Bandits with Knapsacks.
On Mixtures of Markov Chains.
Stochastic Optimization for Large-scale Optimal Transport.
Local Minimax Complexity of Stochastic Convex Optimization.
Leveraging Sparsity for Efficient Submodular Data Summarization.
Discriminative Gaifman Models.
Deep Submodular Functions: Definitions and Learning.
Synthesizing the preferred inputs for neurons in neural networks via deep generator networks.
An equivalence between high dimensional Bayes optimal inference and M-estimation.
Split LBI: An Iterative Regularization Path with Structural Sparsity.
Exponential expressivity in deep neural networks through transient chaos.
Higher-Order Factorization Machines.
Search Improves Label for Active Learning.
Interpretable Nonlinear Dynamic Modeling of Neural Trajectories.
Scaled Least Squares Estimator for GLMs in Large-Scale Problems.
Equality of Opportunity in Supervised Learning.
A Non-generative Framework and Convex Relaxations for Unsupervised Learning.
Unsupervised Learning from Noisy Networks with Applications to Hi-C Data.
Convergence guarantees for kernel-based quadrature rules in misspecified settings.
Designing smoothing functions for improved worst-case competitive ratio in online optimization.
Automatic Neuron Detection in Calcium Imaging Data Using Convolutional Networks.
Confusions over Time: An Interpretable Bayesian Model to Characterize Trends in Decision Making.
Structured Matrix Recovery via the Generalized Dantzig Selector.
Deconvolving Feedback Loops in Recommender Systems.
Parameter Learning for Log-supermodular Distributions.
Attend, Infer, Repeat: Fast Scene Understanding with Generative Models.
Clustering with Same-Cluster Queries.
NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization.
Pairwise Choice Markov Chains.
Learning shape correspondence with anisotropic convolutional neural networks.
"Congruent" and "Opposite" Neurons: Sisters for Multisensory Integration and Segregation.
Launch and Iterate: Reducing Prediction Churn.
Finite-Dimensional BFRY Priors and Variational Bayesian Inference for Power Law Models.
Optimistic Gittins Indices.
Consistent Estimation of Functions of Data Missing Non-Monotonically and Not at Random.
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits.
The Parallel Knowledge Gradient Method for Batch Bayesian Optimization.
New Liftable Classes for First-Order Probabilistic Inference.
MoCap-guided Data Augmentation for 3D Pose Estimation in the Wild.
High resolution neural connectivity from incomplete tracing data using nonnegative spline regression.
On Robustness of Kernel Clustering.
Learning Sensor Multiplexing Design through Back-propagation.
Estimating the Size of a Large Network and its Communities from a Random Sample.
Learning Infinite RBMs with Frank-Wolfe.
A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order.
Maximization of Approximately Submodular Functions.
Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation.
Showing versus doing: Teaching by demonstration.
Variational Bayes on Monte Carlo Steroids.
Stochastic Gradient Geodesic MCMC Methods.
Sub-sampled Newton Methods with Non-uniform Sampling.
Adaptive Averaging in Accelerated Descent Dynamics.
The Multiscale Laplacian Graph Kernel.
Matrix Completion has No Spurious Local Minimum.
Combinatorial semi-bandit with known covariance.
Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling.
Composing graphical models with neural networks for structured representations and fast inference.
Stochastic Gradient MCMC with Stale Gradients.
Conditional Generative Moment-Matching Networks.
Fast and Flexible Monotonic Functions with Ensembles of Lattices.
Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition.
A Probabilistic Model of Social Decision Making based on Reward Maximization.
Bayesian optimization for automated model selection.
Robust k-means: a Theoretical Revisit.
Regret Bounds for Non-decomposable Metrics with Missing Labels.
Learning HMMs with Nonparametric Emissions via Spectral Decompositions of Continuous Matrices.
On Multiplicative Integration with Recurrent Neural Networks.
Can Peripheral Representations Improve Clutter Metrics on Complex Scenes?
Improved Error Bounds for Tree Representations of Metric Spaces.
Statistical Inference for Pairwise Graphical Models Using Score Matching.
Active Learning with Oracle Epiphany.
Object based Scene Representations using Fisher Scores of Local Subspace Projections.
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections.
Generative Shape Models: Joint Text Recognition and Segmentation with Very Little Training Data.
Supervised learning through the lens of compression.
Using Social Dynamics to Make Individual Predictions: Variational Inference with a Stochastic Kinetic Model.
Dimensionality Reduction of Massive Sparse Datasets Using Coresets.
The non-convex Burer-Monteiro approach works on smooth semidefinite programs.
Quantized Random Projections and Non-Linear Estimation of Cosine Similarity.
Bi-Objective Online Matching and Submodular Allocations.
Learning under uncertainty: a comparison between R-W and Bayesian approach.
Learning Bound for Parameter Transfer Learning.
Feature-distributed sparse regression: a screen-and-clean approach.
Finite Sample Prediction and Recovery Bounds for Ordinal Embedding.
Kronecker Determinantal Point Processes.
Estimating the class prior and posterior from noisy positives and unlabeled data.
Global Analysis of Expectation Maximization for Mixtures of Two Gaussians.
Deep Neural Networks with Inexact Matching for Person Re-Identification.
Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions.
Causal meets Submodular: Subset Selection with Directed Information.
Probabilistic Inference with Generating Functions for Poisson Latent Variable Models.
Nearly Isometric Embedding by Relaxation.
Reshaped Wirtinger Flow for Solving Quadratic System of Equations.
Measuring Neural Net Robustness with Constraints.
Long-term Causal Effects via Behavioral Game Theory.
Interaction Screening: Efficient and Sample-Optimal Learning of Ising Models.
Stochastic Variational Deep Kernel Learning.
Single Pass PCA of Matrix Products.
General Tensor Spectral Co-clustering for Higher-Order Data.
A Probabilistic Framework for Deep Learning.
Error Analysis of Generalized Nyström Kernel Regression.
Constraints Based Convex Belief Propagation.
Improved Dropout for Shallow and Deep Learning.
Structured Prediction Theory Based on Factor Graph Complexity.
Geometric Dirichlet Means Algorithm for topic inference.
Hypothesis Testing in Unsupervised Domain Adaptation with Applications in Alzheimer's Disease.
Maximizing Influence in an Ising Network: A Mean-Field Optimal Solution.
Graph Clustering: Block-models and model free results.
Selective inference for group-sparse linear models.
Breaking the Bandwidth Barrier: Geometrical Adaptive Entropy Estimation.
Measuring the reliability of MCMC inference with bidirectional Monte Carlo.
Eliciting Categorical Data for Optimal Aggregation.
Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Games.
Deep Learning for Predicting Human Strategic Behavior.
Satisfying Real-world Goals with Dataset Constraints.
Universal Correspondence Network.
Blind Attacks on Machine Learners.
Contextual semibandits via supervised learning oracles.
A Bio-inspired Redundant Sensing Architecture.
Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm.
Review Networks for Caption Generation.
Variational Autoencoder for Deep Learning of Images, Labels and Captions.
Clustering with Bregman Divergences: an Asymptotic Analysis.
Pruning Random Forests for Prediction on a Budget.
Learning Bayesian networks with ancestral constraints.
Hierarchical Clustering via Spreading Metrics.
Graphons, mergeons, and so on!
Safe Policy Improvement by Minimizing Robust Baseline Regret.
Optimistic Bandit Convex Optimization.
Examples are not enough, learn to criticize! Criticism for Interpretability.
Finding significant combinations of features in the presence of categorical covariates.
Learning the Number of Neurons in Deep Networks.
Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity.
Learning Multiagent Communication with Backpropagation.
DeepMath - Deep Sequence Models for Premise Selection.
Improved Techniques for Training GANs.
Minimizing Quadratic Functions in Constant Time.
Stochastic Gradient Methods for Distributionally Robust Optimization with f-divergences.
Sequential Neural Models with Stochastic Layers.
Mixed Linear Regression with Multiple Components.
Hardness of Online Sleeping Combinatorial Optimization Problems.
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets.
On the Recursive Teaching Dimension of VC Classes.
Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering.
Value Iteration Networks.
Learning to Communicate with Deep Multi-Agent Reinforcement Learning.
Active Learning from Imperfect Labelers.
Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles.
Learning Transferrable Representations for Unsupervised Domain Adaptation.
Brains on Beats.
Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products.
Sample Complexity of Automated Mechanism Design.
Learning Structured Sparsity in Deep Neural Networks.
Learning Influence Functions from Incomplete Observations.
Coordinate-wise Power Method.
Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo.
Tensor Switching Networks.
Inference by Reparameterization in Neural Population Codes.
A Non-parametric Learning Method for Confidently Estimating Patient's Clinical State and Dynamics.
A Probabilistic Programming Approach To Probabilistic Data Analysis.
Bayesian latent structure discovery from multi-neuron recordings.
Diffusion-Convolutional Neural Networks.
Fast Active Set Methods for Online Spike Inference from Calcium Imaging.
Orthogonal Random Features.
Combinatorial Energy Learning for Image Segmentation.
Relevant sparse codes with variational information bottleneck.
Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition.
Adaptive optimal training of animal behavior.
Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels.
Privacy Odometers and Filters: Pay-as-you-Go Composition.
Automated scalable segmentation of neurons from multispectral images.
End-to-End Goal-Driven Web Navigation.
Learned Region Sparsity and Diversity Also Predicts Visual Attention.
Data Poisoning Attacks on Factorization-Based Collaborative Filtering.
PAC-Bayesian Theory Meets Bayesian Inference.
Low-Rank Regression with Tensor Responses.
Unsupervised Learning of Spoken Language with Visual Context.
Improved Deep Metric Learning with Multi-class N-pair Loss Objective.
PAC Reinforcement Learning with Rich Observations.
Statistical Inference for Cluster Trees.
Architectural Complexity Measures of Recurrent Neural Networks.
A Bandit Framework for Strategic Regression.
A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification.
Bootstrap Model Aggregation for Distributed Statistical Learning.
Anchor-Free Correlated Topic Modeling: Identifiability and Algorithm.
The Multi-fidelity Multi-armed Bandit.
Correlated-PCA: Principal Components' Analysis when Data and Noise are Correlated.
Variational Inference in Mixed Probabilistic Submodular Models.
Scalable Adaptive Stochastic Optimization Using Random Projections.
Towards Unifying Hamiltonian Monte Carlo and Slice Sampling.
Consistent Kernel Mean Estimation for Functions of Random Variables.
Reward Augmented Maximum Likelihood for Neural Structured Prediction.
Accelerating Stochastic Composition Optimization.
A Credit Assignment Compiler for Joint Prediction.
Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision.
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods.
Deep Learning Games.
Regret of Queueing Bandits.
Boosting with Abstention.
Combinatorial Multi-Armed Bandit with General Reward Functions.
Exploiting the Structure: Stochastic Gradient Methods Using Raw Clusters.
A Non-convex One-Pass Framework for Generalized Factorization Machine and Rank-One Matrix Sensing.
Robustness of classifiers: from adversarial to random noise.
On Valid Optimal Assignment Kernels and Applications to Graph Classification.
Optimal Black-Box Reductions Between Optimization Objectives.
Multiple-Play Bandits in the Position-Based Model.
Adaptive Skills Adaptive Partitions (ASAP).
Identification and Overidentification of Linear Structural Equation Models.
Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs.
Observational-Interventional Priors for Dose-Response Learning.
Learning Tree Structured Potential Games.
Generating Long-term Trajectories Using Deep Hierarchical Networks.
SEBOOST - Boosting Stochastic Learning Using Subspace Optimization Techniques.
Understanding Probabilistic Sparse Gaussian Process Approximations.
Structured Sparse Regression via Greedy Hard Thresholding.
Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation.
Simple and Efficient Weighted Minwise Hashing.
Stochastic Structured Prediction under Bandit Feedback.
Large Margin Discriminant Dimensionality Reduction in Prediction Space.
Unifying Count-Based Exploration and Intrinsic Motivation.
Learning Treewidth-Bounded Bayesian Networks with Thousands of Variables.
Synthesis of MCMC and Belief Propagation.
Adaptive Neural Compilation.
Bayesian optimization under mixed constraints with a slack-variable augmented Lagrangian.
Catching heuristics are optimal control policies.
Flexible Models for Microclustering with Application to Entity Resolution.
Stochastic Variance Reduction Methods for Saddle-Point Problems.
End-to-End Kernel Learning with Supervised Convolutional Kernel Networks.
A Pseudo-Bayesian Algorithm for Robust PCA.
Learning a Metric Embedding for Face Recognition using the Multibatch Method.
Dynamic Network Surgery for Efficient DNNs.
Preference Completion from Partial Rankings.
Deep Learning Models of the Retinal Response to Natural Scenes.
Nested Mini-Batch K-Means.
Adaptive Concentration Inequalities for Sequential Decision Problems.
Achieving the KS threshold in the general stochastic block model with linearized acyclic belief propagation.
Mixed vine copulas as joint models of spike counts and local field potentials.
Crowdsourced Clustering: Querying Edges vs Triangles.
Optimal Tagging with Markov Chain Optimization.
Learning Kernels with Random Features.
Sampling for Bayesian Program Learning.
Convex Two-Layer Modeling with Latent Structure.
A Communication-Efficient Parallel Algorithm for Decision Tree.
Local Similarity-Aware Deep Feature Embedding.
Dueling Bandits: Beyond Condorcet Winners to General Tournament Solutions.
Adaptive Maximization of Pointwise Submodular Functions With Budget Constraint.
What Makes Objects Similar: A Unified Multi-Metric Learning Approach.
A state-space model of cross-region dynamic connectivity in MEG/EEG.
Finite-Sample Analysis of Fixed-k Nearest Neighbor Density Functional Estimators.
Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than O(1/\epsilon).
Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning.
Refined Lower Bounds for Adversarial Bandits.
Causal Bandits: Learning Good Interventions via Causal Inference.
Dense Associative Memory for Pattern Recognition.
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning.
Variance Reduction in Stochastic Gradient Langevin Dynamics.
Proximal Stochastic Methods for Nonsmooth Nonconvex Finite-Sum Optimization.
Multi-view Anomaly Detection via Robust Probabilistic Latent Variable Models.
Solving Marginal MAP Problems with NP Oracles and Parity Constraints.
Generalized Correspondence-LDA Models (GC-LDA) for Identifying Functional Regions in the Brain.
VIME: Variational Information Maximizing Exploration.
How Deep is the Feature Analysis underlying Rapid Visual Categorization?
Density Estimation via Discrepancy Based Adaptive Sequential Partition.
Doubly Convolutional Neural Networks.
Rényi Divergence Variational Inference.
Semiparametric Differential Graph Models.
A Multi-Batch L-BFGS Method for Machine Learning.
Safe and Efficient Off-Policy Reinforcement Learning.
Direct Feedback Alignment Provides Learning in Deep Neural Networks.
Fast ε-free Inference of Simulation Models with Bayesian Conditional Density Estimation.
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks.
Efficient Nonparametric Smoothness Estimation.
Linear-Memory and Decomposition-Invariant Linearly Convergent Conditional Gradient Algorithm for Structured Polytopes.
Gaussian Process Bandit Optimisation with Multi-fidelity Evaluations.
An algorithm for L1 nearest neighbor search via monotonic embedding.
Even Faster SVD Decomposition Yet Without Agonizing Pain.
Optimal Cluster Recovery in the Labeled Stochastic Block Model.
Differential Privacy without Sensitivity.
PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions.
Efficient and Robust Spiking Neural Circuit for Navigation Inspired by Echolocating Bats.
The Robustness of Estimator Composition.
Distributed Flexible Nonlinear Tensor Factorization.
Dynamic Mode Decomposition with Reproducing Kernels for Koopman Spectral Analysis.
Efficient Second Order Online Learning by Sketching.
Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks.
SoundNet: Learning Sound Representations from Unlabeled Video.
Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach.
Faster Projection-free Convex Optimization over the Spectrahedron.
Proximal Deep Structured Models.
Active Nearest-Neighbor Learning in Metric Spaces.
Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction.
Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognition.
Dialog-based Language Learning.
Dual Learning for Machine Translation.
Deep Alternative Neural Network: Exploring Contexts as Early as Possible for Action Recognition.
DECOrrelated feature space partitioning for distributed sparse regression.
Sublinear Time Orthogonal Tensor Decomposition.
On Explore-Then-Commit strategies.
The Power of Adaptivity in Identifying Statistical Alternatives.
Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis.
An ensemble diversity approach to supervised binary hashing.
Online Convex Optimization with Unconstrained Domains and Losses.
Computational and Statistical Tradeoffs in Learning to Rank.
Single-Image Depth Perception in the Wild.
SPALS: Fast Alternating Least Squares via Implicit Leverage Scores Sampling.
Regularized Nonlinear Acceleration.
Optimal spectral transportation with application to music transcription.
On Graph Reconstruction via Empirical Risk Minimization: Fast Learning Rates and Scalability.
Barzilai-Borwein Step Size for Stochastic Gradient Descent.
A Simple Practical Accelerated Method for Finite Sums.
Dynamic Filter Networks.
Generating Images with Perceptual Similarity Metrics based on Deep Networks.
Double Thompson Sampling for Dueling Bandits.
Optimizing affinity-based binary hashing using auxiliary coordinates.
A Powerful Generative Model Using Random Weights for the Deep Image Representation.
Neurally-Guided Procedural Models: Amortized Inference for Procedural Graphics Programs using Neural Networks.
Generating Videos with Scene Dynamics.
A Constant-Factor Bi-Criteria Approximation Guarantee for k-means++.
Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity.
Deep Learning without Poor Local Minima.
Coin Betting and Parameter-Free Online Learning.
Solving Random Systems of Quadratic Equations via Truncated Generalized Gradient Flow.
Adversarial Multiclass Classification: A Risk Minimization Perspective.
Residual Networks Behave Like Ensembles of Relatively Shallow Networks.
Robust Spectral Detection of Global Structures in the Data by Learning a Regularization.
Learning User Perceived Clusters with Feature-Level Supervision.
Learning feed-forward one-shot learners.
Budgeted stream-based active learning via adaptive submodular maximization.
Fast learning rates with heavy-tailed losses.
Operator Variational Inference.
Variational Information Maximization for Feature Selection.
Exponential Family Embeddings.
Coupled Generative Adversarial Networks.
The Generalized Reparameterization Gradient.
Stochastic Online AUC Maximization.
Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images.
A Unified Approach for Learning the Parameters of Sum-Product Networks.
Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula.
Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks.
Gradient-based Sampling: An Adaptive Importance Sampling for Least-squares.
Learning and Forecasting Opinion Dynamics in Social Networks.
GAP Safe Screening Rules for Sparse-Group Lasso.
R-FCN: Object Detection via Region-based Fully Convolutional Networks.
CMA-ES with Optimal Covariance Update and Storage Complexity.
Multimodal Residual Learning for Visual QA.
DISCO Nets : DISsimilarity COefficients Networks.
Domain Separation Networks.
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization.
Fairness in Learning: Classic and Contextual Bandits.
CRF-CNN: Modeling Structured Information in Human Pose Estimation.
FPNN: Field Probing Neural Networks for 3D Data.
Optimal Sparse Linear Encoders and Sparse PCA.
Hierarchical Question-Image Co-Attention for Visual Question Answering.
Bayesian Optimization for Probabilistic Programs.
f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization.
Cooperative Graphical Models.
CNNpack: Packing Convolutional Neural Networks in the Frequency Domain.
Learning from Small Sample Sets by Combining Unsupervised Meta-Training with CNNs.
Integrated perception with recurrent multi-task neural networks.
The Sound of APALM Clapping: Faster Nonsmooth Nonconvex Optimization with Stochastic Asynchronous PALM.
Learning What and Where to Draw.
Multivariate tests of association based on univariate tests.
Multi-armed Bandits: Competing with Optimal Sequences.
Sorting out typicality with the inverse moment matrix SOS polynomial.
Interpretable Distribution Features with Maximum Testing Power.
SURGE: Surface Regularized Geometry Estimation from a Single Image.
Linear dynamical neural population models through nonlinear embeddings.
Minimizing Regret on Reflexive Banach Spaces and Nash Equilibria in Continuous Zero-Sum Games.
Verification Based Solution for Structured MAB Problems.
Unsupervised Domain Adaptation with Residual Transfer Networks.
Tree-Structured Reinforcement Learning for Sequential Object Localization.
Natural-Parameter Networks: A Class of Probabilistic Neural Networks.
Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognition.
Human Decision-Making under Limited Time.
Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks.
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling.
High-Rank Matrix Completion and Clustering under Self-Expressive Models.
Unsupervised Learning for Physical Interaction through Video Prediction.
Fast and Provably Good Seedings for k-Means.
Without-Replacement Sampling for Stochastic Gradient Methods.
On Regularizing Rademacher Observation Losses.
Swapout: Learning an ensemble of deep architectures.
A scaled Bregman theorem with applications.
Deep ADMM-Net for Compressive Sensing MRI.
Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much.
