ICLR 2018 论文列表
6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Workshop Track Proceedings.
|
Winner's Curse? On Pace, Progress, and Empirical Rigor.
Nonlinear Acceleration of CNNs.
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning.
A Dataset To Evaluate The Representations Learned By Video Prediction Models.
Depth separation and weight-width trade-offs for sigmoidal neural networks.
Learning Invariance with Compact Transforms.
Semi-Supervised Learning With GANs: Revisiting Manifold Regularization.
Learning and Memorization.
Weighted Geodesic Distance Following Fermat's Principle.
Gradient-based Optimization of Neural Network Architecture.
Adapting to Continuously Shifting Domains.
Selecting the Best in GANs Family: a Post Selection Inference Framework.
Towards Variational Generation of Small Graphs.
TransNets for Review Generation.
Isolating Sources of Disentanglement in Variational Autoencoders.
PixelSNAIL: An Improved Autoregressive Generative Model.
Iterative GANs for Rotating Visual Objects.
Learning and Analyzing Vector Encoding of Symbolic Representation.
Scalable Estimation via LSH Samplers (LSS).
Feature-Based Metrics for Exploring the Latent Space of Generative Models.
Wasserstein Auto-Encoders: Latent Dimensionality and Random Encoders.
Bayesian Incremental Learning for Deep Neural Networks.
Rethinking Style and Content Disentanglement in Variational Autoencoders.
Compression by the signs: distributed learning is a two-way street.
In reinforcement learning, all objective functions are not equal.
Monotonic models for real-time dynamic malware detection.
HoME: a Household Multimodal Environment.
Online variance-reducing optimization.
The Mirage of Action-Dependent Baselines in Reinforcement Learning.
Practical Hyperparameter Optimization for Deep Learning.
Conditional Networks for Few-Shot Semantic Segmentation.
Learning to Learn Without Labels.
Realistic Evaluation of Semi-Supervised Learning Algorithms.
A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training.
Inference in probabilistic graphical models by Graph Neural Networks.
Faster Neural Networks Straight from JPEG.
Learning Invariances for Policy Generalization.
Stochastic Gradient Langevin dynamics that Exploit Neural Network Structure.
Neural network parameter regression for lattice quantum chromodynamics simulations in nuclear and particle physics.
Efficient Recurrent Neural Networks using Structured Matrices in FPGAs.
Black-box Attacks on Deep Neural Networks via Gradient Estimation.
Attacking the Madry Defense Model with $L_1$-based Adversarial Examples.
Understanding the Loss Surface of Single-Layered Neural Networks for Binary Classification.
SpectralWords: Spectral Embeddings Approach to Word Similarity Task for Large Vocabularies.
Hockey-Stick GAN.
On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples.
Decoupling Dynamics and Reward for Transfer Learning.
Spatially Parallel Convolutions.
LSTM Iteration Networks: An Exploration of Differentiable Path Finding.
Learning Rich Image Representation with Deep Layer Aggregation.
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values.
Towards Specification-Directed Program Repair.
eCommerceGAN: A Generative Adversarial Network for e-commerce.
Concept Learning with Energy-Based Models.
GILBO: One Metric to Measure Them All.
GitGraph - from Computational Subgraphs to Smaller Architecture Search Spaces.
An interpretable LSTM neural network for autoregressive exogenous model.
Towards Mixed-initiative generation of multi-channel sequential structure.
Semiparametric Reinforcement Learning.
Resilient Backpropagation (Rprop) for Batch-learning in TensorFlow.
3D-FilterMap: A Compact Architecture for Deep Convolutional Neural Networks.
Pelee: A Real-Time Object Detection System on Mobile Devices.
IamNN: Iterative and Adaptive Mobile Neural Network for efficient image classification.
Causal Discovery Using Proxy Variables.
Synthesizing Audio with GANs.
Minimally Redundant Laplacian Eigenmaps.
An Evaluation of Fisher Approximations Beyond Kronecker Factorization.
Combating Adversarial Attacks Using Sparse Representations.
Meta-Learning for Batch Mode Active Learning.
DiCE: The Infinitely Differentiable Monte-Carlo Estimator.
Generative Modeling for Protein Structures.
Universal Successor Representations for Transfer Reinforcement Learning.
SufiSent - Universal Sentence Representations Using Suffix Encodings.
Finding Flatter Minima with SGD.
Censoring Representations with Multiple-Adversaries over Random Subspaces.
Deep Convolutional Malware Classifiers Can Learn from Raw Executables and Labels Only.
A differentiable BLEU loss. Analysis and first results.
Meta-Learning a Dynamical Language Model.
Reconstructing evolutionary trajectories of mutations in cancer.
Policy Optimization with Second-Order Advantage Information.
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning.
Learning Longer-term Dependencies in RNNs with Auxiliary Losses.
Are Efficient Deep Representations Learnable?
Easing non-convex optimization with neural networks.
A Language and Compiler View on Differentiable Programming.
ShakeDrop regularization.
Stacked Filters Stationary Flow For Hardware-Oriented Acceleration Of Deep Convolutional Neural Networks.
Semi-Supervised Few-Shot Learning with MAML.
An Experimental Study of Neural Networks for Variable Graphs.
ComboGAN: Unrestricted Scalability for Image Domain Translation.
Additive Margin Softmax for Face Verification.
Designing Efficient Neural Attention Systems Towards Achieving Human-level Sharp Vision.
Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers.
Expert-based reward function training: the novel method to train sequence generators.
PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures.
Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks.
SGD on Random Mixtures: Private Machine Learning under Data Breach Threats.
Learning How Not to Act in Text-based Games.
DeepNCM: Deep Nearest Class Mean Classifiers.
Efficient Entropy For Policy Gradient with Multi-Dimensional Action Space.
Adaptive Path-Integral Approach for Representation Learning and Planning.
Learning Disentangled Representations with Wasserstein Auto-Encoders.
Multi-Agent Generative Adversarial Imitation Learning.
Leveraging Constraint Logic Programming for Neural Guided Program Synthesis.
Extending Robust Adversarial Reinforcement Learning Considering Adaptation and Diversity.
Uncertainty Estimation via Stochastic Batch Normalization.
Jointly Learning "What" and "How" from Instructions and Goal-States.
Analysis of Cosmic Microwave Background with Deep Learning.
Learning via social awareness: improving sketch representations with facial feedback.
Reward Estimation for Variance Reduction in Deep Reinforcement Learning.
Tempered Adversarial Networks.
Stable and Effective Trainable Greedy Decoding for Sequence to Sequence Learning.
An Optimization View on Dynamic Routing Between Capsules.
Differentiable Neural Network Architecture Search.
Predicting Embryo Morphokinetics in Videos with Late Fusion Nets & Dynamic Decoders.
NAM - Unsupervised Cross-Domain Image Mapping without Cycles or GANs.
Coupled Ensembles of Neural Networks.
Clustering Meets Implicit Generative Models.
Deep Neural Maps.
Evaluating visual "common sense" using fine-grained classification and captioning tasks.
MemCNN: a Framework for Developing Memory Efficient Deep Invertible Networks.
A moth brain learns to read MNIST.
ReinforceWalk: Learning to Walk in Graph with Monte Carlo Tree Search.
ChatPainter: Improving Text to Image Generation using Dialogue.
Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks.
3D-Scene-GAN: Three-dimensional Scene Reconstruction with Generative Adversarial Networks.
Negative eigenvalues of the Hessian in deep neural networks.
GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks.
Learning to Infer.
Parametric Adversarial Divergences are Good Task Losses for Generative Modeling.
Adaptive Memory Networks.
Reinforcement Learning from Imperfect Demonstrations.
PDE-Net: Learning PDEs from Data.
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations.
Regret Minimization for Partially Observable Deep Reinforcement Learning.
Autoregressive Generative Adversarial Networks.
DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images.
Rotational Unit of Memory.
Learning to Organize Knowledge with N-Gram Machines.
Challenges in Disentangling Independent Factors of Variation.
Shifting Mean Activation Towards Zero with Bipolar Activation Functions.
Aspect-based Question Generation.
Tree-to-tree Neural Networks for Program Translation.
Exponentially vanishing sub-optimal local minima in multilayer neural networks.
Weightless: Lossy weight encoding for deep neural network compression.
The loss surface and expressivity of deep convolutional neural networks.
Graph Partition Neural Networks for Semi-Supervised Classification.
Regularization Neural Networks via Constrained Virtual Movement Field.
Empirical Analysis of the Hessian of Over-Parametrized Neural Networks.
Covariant Compositional Networks For Learning Graphs.
Learning Deep Models: Critical Points and Local Openness.
Extending the Framework of Equilibrium Propagation to General Dynamics.
Cold fusion: Training Seq2seq Models Together with Language Models.
Learning Representations and Generative Models for 3D Point Clouds.
Lsh-Sampling breaks the Computational chicken-and-egg Loop in adaptive stochastic Gradient estimation.
No Spurious Local Minima in a Two Hidden Unit ReLU Network.
Intriguing Properties of Adversarial Examples.
Neuron as an Agent.
Kronecker Recurrent Units.
Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms.
Variance-based Gradient Compression for Efficient Distributed Deep Learning.
Adversarial Policy Gradient for Alternating Markov Games.
DLVM: A modern compiler infrastructure for deep learning systems.
Faster Discovery of Neural Architectures by Searching for Paths in a Large Model.
Accelerating Neural Architecture Search using Performance Prediction.
Benefits of Depth for Long-Term Memory of Recurrent Networks.
Searching for Activation Functions.
Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks.
Convolutional Sequence Modeling Revisited.
Simple and efficient architecture search for Convolutional Neural Networks.
A Flexible Approach to Automated RNN Architecture Generation.
Multiple Source Domain Adaptation with Adversarial Learning.
Distributional Adversarial Networks.
Time-Dependent Representation for Neural Event Sequence Prediction.
Stable Distribution Alignment Using the Dual of the Adversarial Distance.
Adversarial Spheres.
Predict Responsibly: Increasing Fairness by Learning to Defer.
Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design.
Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?
Fast Node Embeddings: Learning Ego-Centric Representations.
The Effectiveness of a two-Layer Neural Network for Recommendations.
Neural Program Search: Solving Programming Tasks from Description and Examples.
Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies.
To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression.
Automated Design using Neural Networks and Gradient Descent.
Building Generalizable Agents with a Realistic and Rich 3D Environment.
Learning Efficient Tensor Representations with Ring Structure Networks.
Deep learning mutation prediction enables early stage lung cancer detection in liquid biopsy.
Fast and Accurate Text Classification: Skimming, Rereading and Early Stopping.
FigureQA: An Annotated Figure Dataset for Visual Reasoning.
Towards Provable Control for Unknown Linear Dynamical Systems.
Gradients explode - Deep Networks are shallow - ResNet explained.
Investigating Human Priors for Playing Video Games.
Capturing Human Category Representations by Sampling in Deep Feature Spaces.
Feature Incay for Representation Regularization.
