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
VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search
Watch, Try, Learn: Meta-Learning from Demonstrations and Rewards
Weakly Supervised Clustering by Exploiting Unique Class Count
Weakly Supervised Disentanglement with Guarantees
What Can Neural Networks Reason About?
What Can You Learn From Your Muscles? Learning Visual Representation from Human Interactions
What graph neural networks cannot learn: depth vs width
White Noise Analysis of Neural Networks
Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity
Why Not to Use Zero Imputation? Correcting Sparsity Bias in Training Neural Networks
word2ket: Space-efficient Word Embeddings inspired by Quantum Entanglement
You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings
You Only Train Once: Loss-Conditional Training of Deep Networks
Your classifier is secretly an energy based model and you should treat it like one

« prev Page 15/15