ICLR 2020

718 papers

Top Research Directions

Research directions most represented by ICLR 2020 papers.

The Mechanics of Benign Overfitting in High Dimensions 14
Sample Efficient Reinforcement Learning 12
Clean Accuracy Degradation in Machine Learning Defenses 12
Bypassing the Computational Bottleneck of Adversarial Training 11
Optimization and Generalization with Non-Smooth Activations 10
Accelerating Neural Architecture Search Without Full Model Training 10
Mitigating Input Perturbation Sensitivity in Deep Networks 10
The Computational Overhead of Iterative Model Pruning 8
Mitigating Gradient Variance in Policy Optimization 8
Exploration Strategies for Sparse Reward Reinforcement Learning 8
Mitigating Posterior Collapse in Latent Variable Models 7
Harnessing Parameter Redundancy in Deep Neural Networks 7
Why Differentiable Architecture Search Collapses to Skip Connections 6
Learning Minimal Sufficient Representations via Information Bottlenecks 6
Linearizing Deep Learning via the Neural Tangent Kernel 6

Top Authors

AuthorPapers
Sergey Levine13
Jun Zhu7
Cho-Jui Hsieh6
Liwei Wang6
Pushmeet Kohli6
Yoshua Bengio6
Anirudh Goyal5
Chelsea Finn5
Martin Jaggi5
Tom Goldstein5
Abhinav Gupta4
Deva Ramanan4
Eunho Yang4
Frank Hutter4
Graham Neubig4
Jiatao Gu4
Kyunghyun Cho4
Matthew Botvinick4
Max Welling4
Quanquan Gu4

Impactful Papers

Papers from ICLR 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension
Neural tangent kernels, transportation mappings, and universal approximation
Neural Tangents: Fast and Easy Infinite Neural Networks in Python
Neural Text Generation With Unlikelihood Training
NeurQuRI: Neural Question Requirement Inspector for Answerability Prediction in Machine Reading Comprehension
Never Give Up: Learning Directed Exploration Strategies
Non-Autoregressive Dialog State Tracking
Normalized Attention Without Probability Cage
Novelty Detection Via Blurring
Object-Centric Neural Scene Rendering
Oblique Decision Trees from Derivatives of ReLU Networks
Observational Overfitting in Reinforcement Learning
On Adversarial Bias and the Robustness of Fair Machine Learning
On Bonus Based Exploration Methods In The Arcade Learning Environment
Once-for-All: Train One Network and Specialize it for Efficient Deployment
On Computation and Generalization of Generative Adversarial Imitation Learning
One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation
On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning
On Identifiability in Transformers
Online and stochastic optimization beyond Lipschitz continuity: A Riemannian approach
On Mutual Information Maximization for Representation Learning
On Robustness of Neural Ordinary Differential Equations
On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach
On the Convergence of FedAvg on Non-IID Data
On the Equivalence between Positional Node Embeddings and Structural Graph Representations
On the Global Convergence of Training Deep Linear ResNets
On the interaction between supervision and self-play in emergent communication
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
On the Relationship between Self-Attention and Convolutional Layers
On the "steerability" of generative adversarial networks
On the Variance of the Adaptive Learning Rate and Beyond
On the Weaknesses of Reinforcement Learning for Neural Machine Translation
On Universal Equivariant Set Networks
Optimal Strategies Against Generative Attacks
Optimistic Exploration even with a Pessimistic Initialisation
Option Discovery using Deep Skill Chaining
Order Learning and Its Application to Age Estimation
Overlearning Reveals Sensitive Attributes
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks
PairNorm: Tackling Oversmoothing in GNNs
Pay Attention to Features, Transfer Learn Faster CNNs
PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
PCMC-Net: Feature-based Pairwise Choice Markov Chains
Permutation Equivariant Models for Compositional Generalization in Language
Phase Transitions for the Information Bottleneck in Representation Learning
Physics-as-Inverse-Graphics: Unsupervised Physical Parameter Estimation from Video
Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics
Picking Winning Tickets Before Training by Preserving Gradient Flow
Piecewise linear activations substantially shape the loss surfaces of neural networks

« prev Page 10/15 next »