ICLR 2019

514 papers

Top Research Directions

Research directions most represented by ICLR 2019 papers.

Exploration Strategies for Sparse Reward Reinforcement Learning 9
Step Level Feedback for Long Horizon Reinforcement Learning 8
Mitigating Gradient Variance in Policy Optimization 7
Navigating Non-Convex Loss Landscapes in Deep Learning 7
Mitigating Discriminator Saturation in Adversarial Learning 7
Sample Efficient Reinforcement Learning 7
Clean Accuracy Degradation in Machine Learning Defenses 7
Lipschitz Regularization for Stable Neural Networks 6
Mitigating Posterior Collapse in Latent Variable Models 6
First-Order Approximations for Efficient Meta-Learning 6
The Reward Engineering Bottleneck in Reinforcement Learning 6
The Computational Bottleneck of Stochastic Uncertainty Estimation 6
The Dynamics of Minimax Optimization Instability 6
Understanding Gradient Masking in Adversarial Defenses 6
Learning Minimal Sufficient Representations via Information Bottlenecks 5

Top Authors

AuthorPapers
Sergey Levine15
Yoshua Bengio12
Joshua B. Tenenbaum8
Jiajun Wu7
Nicolas Heess6
Oriol Vinyals6
Pushmeet Kohli6
Abhinav Gupta5
Caiming Xiong5
Matthias Bethge5
Pieter Abbeel5
Roger Baker Grosse5
Abhishek Gupta4
Amos Storkey4
Chelsea Finn4
Dawn Song4
Felix Hill4
José Miguel Hernández-Lobato4
Pin-Yu Chen4
Razvan Pascanu4

Impactful Papers

Papers from ICLR 2019 that shaped research clusters.

Foundational

Influential

Papers

Title
On the Turing Completeness of Modern Neural Network Architectures
On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks
Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
Optimal Completion Distillation for Sequence Learning
Optimal Control Via Neural Networks: A Convex Approach
Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative Models
Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile
Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation
Overcoming the Disentanglement vs Reconstruction Trade-off via Jacobian Supervision
PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
Pay Less Attention with Lightweight and Dynamic Convolutions
PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm
Phase-Aware Speech Enhancement with Deep Complex U-Net
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Poincare Glove: Hyperbolic Word Embeddings
Policy Transfer with Strategy Optimization
Posterior Attention Models for Sequence to Sequence Learning
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
Practical lossless compression with latent variables using bits back coding
Preconditioner on Matrix Lie Group for SGD
Predicting the Generalization Gap in Deep Networks with Margin Distributions
Predict then Propagate: Graph Neural Networks meet Personalized PageRank
Preferences Implicit in the State of the World
Preventing Posterior Collapse with delta-VAEs
Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors
Probabilistic Planning with Sequential Monte Carlo methods
Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning
ProbGAN: Towards Probabilistic GAN with Theoretical Guarantees
ProMP: Proximal Meta-Policy Search
ProxQuant: Quantized Neural Networks via Proximal Operators
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
Pure and Spurious Critical Points: a Geometric Study of Linear Networks
Quasi-hyperbolic momentum and Adam for deep learning
Quaternion Recurrent Neural Networks
Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach
Random mesh projectors for inverse problems
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Recall Traces: Backtracking Models for Efficient Reinforcement Learning
Recurrent Experience Replay in Distributed Reinforcement Learning
Regularized Learning for Domain Adaptation under Label Shifts
Regularized Learning for Domain Adaptation under Label Shifts.
Relational Forward Models for Multi-Agent Learning
Relaxed Quantization for Discretized Neural Networks
RelGAN: Relational Generative Adversarial Networks for Text Generation
Representation Degeneration Problem in Training Natural Language Generation Models
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
Residual Non-local Attention Networks for Image Restoration
Rethinking the Value of Network Pruning

« prev Page 8/11 next »