NeurIPS 2020

1,908 papers

Top Research Directions

Research directions most represented by NeurIPS 2020 papers.

Clean Accuracy Degradation in Machine Learning Defenses 21
Bypassing the Computational Bottleneck of Adversarial Training 20
Scaling Gaussian Processes Beyond Cubic Complexity 19
Safe Reinforcement Learning via Constrained Markov Decision Processes 17
The Non-Linear Function Approximation Gap in Reinforcement Learning 17
The Mechanics of Benign Overfitting in High Dimensions 15
Optimization and Generalization with Non-Smooth Activations 14
Multi-Agent Learning Under Bandit Feedback 13
Mitigating Gradient Variance in Policy Optimization 13
The Infinite Width Approximation Gap in Deep Learning 12
The Statistical Computational Gap in High Dimensions 12
Scaling Bandit Learning to Large Action Spaces 12
The Function Approximation Gap in Reinforcement Learning Theory 12
Linearizing Deep Learning via the Neural Tangent Kernel 11
Sample Efficient Reinforcement Learning 11

Top Authors

AuthorPapers
Sergey Levine11
Mihaela van der Schaar10
Csaba Szepesvari9
Jinwoo Shin9
Michael W. Mahoney9
Stefano Ermon9
Sung Ju Hwang9
Zhaoran Wang9
Pieter Abbeel8
Zhangyang Wang8
Zhuoran Yang8
Andreas Krause7
Bo Dai7
Dacheng Tao7
Jason D. Lee7
Jun Zhu7
Masashi Sugiyama7
Michael Jordan7
Akshay Krishnamurthy6
Andrea Vedaldi6

Impactful Papers

Papers from NeurIPS 2020 that shaped research clusters.

Foundational

Influential

Papers

Title
Reasoning about Uncertainties in Discrete-Time Dynamical Systems using Polynomial Forms
Reciprocal Adversarial Learning via Characteristic Functions
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate
Reconsidering Generative Objectives For Counterfactual Reasoning
Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN
Recovery of sparse linear classifiers from mixture of responses
Recurrent Quantum Neural Networks
Recurrent Switching Dynamical Systems Models for Multiple Interacting Neural Populations
Recursive Inference for Variational Autoencoders
Reducing Adversarially Robust Learning to Non-Robust PAC Learning
Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization
Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
Regression with reject option and application to kNN
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses
Regret in Online Recommendation Systems
Regularized linear autoencoders recover the principal components, eventually
Regularizing Black-box Models for Improved Interpretability
Regularizing Towards Permutation Invariance In Recurrent Models
Reinforced Molecular Optimization with Neighborhood-Controlled Grammars
Reinforcement Learning for Control with Multiple Frequencies
Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting
Reinforcement Learning with Augmented Data
Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing
Reinforcement Learning with Feedback Graphs
Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension
Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
Relative gradient optimization of the Jacobian term in unsupervised deep learning
Reliable Graph Neural Networks via Robust Aggregation
Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
Reparameterizing Mirror Descent as Gradient Descent
Replica-Exchange Nos\'e-Hoover Dynamics for Bayesian Learning on Large Datasets
Replica-Exchange Nosé-Hoover Dynamics for Bayesian Learning on Large Datasets
RepPoints v2: Verification Meets Regression for Object Detection
Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment
Rescuing neural spike train models from bad MLE
Reservoir Computing meets Recurrent Kernels and Structured Transforms
Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts
Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits
Restoring Negative Information in Few-Shot Object Detection
Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge
Rethinking Importance Weighting for Deep Learning under Distribution Shift
Rethinking Learnable Tree Filter for Generic Feature Transform
Rethinking pooling in graph neural networks
Rethinking Pre-training and Self-training
Rethinking the Value of Labels for Improving Class-Imbalanced Learning
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

« prev Page 30/39 next »