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
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Learning efficient task-dependent representations with synaptic plasticity
Learning Feature Sparse Principal Subspace
Learning from Aggregate Observations
Learning from Failure: De-biasing Classifier from Biased Classifier
Learning from Label Proportions: A Mutual Contamination Framework
Learning from Mixtures of Private and Public Populations
Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
Learning Global Transparent Models consistent with Local Contrastive Explanations
Learning Graph Structure With A Finite-State Automaton Layer
Learning Guidance Rewards with Trajectory-space Smoothing
Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAE
Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning
Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence
Learning Individually Inferred Communication for Multi-Agent Cooperation
Learning Invariances in Neural Networks from Training Data
Learning Invariants through Soft Unification
Learning Kernel Tests Without Data Splitting
Learning Latent Space Energy-Based Prior Model
Learning Linear Programs from Optimal Decisions
Learning Loss for Test-Time Augmentation
Learning Manifold Implicitly via Explicit Heat-Kernel Learning
Learning Multi-Agent Communication through Structured Attentive Reasoning
Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks
Learning Mutational Semantics
Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views
Learning of Discrete Graphical Models with Neural Networks
Learning Optimal Representations with the Decodable Information Bottleneck
Learning outside the Black-Box: The pursuit of interpretable models
Learning Parities with Neural Networks
Learning Physical Constraints with Neural Projections
Learning Physical Graph Representations from Visual Scenes
Learning Representations from Audio-Visual Spatial Alignment
Learning Restricted Boltzmann Machines with Sparse Latent Variables
Learning Retrospective Knowledge with Reverse Reinforcement Learning
Learning Rich Rankings
Learning Robust Decision Policies from Observational Data
Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search
Learning Semantic-aware Normalization for Generative Adversarial Networks
Learning Some Popular Gaussian Graphical Models without Condition Number Bounds
Learning sparse codes from compressed representations with biologically plausible local wiring constraints
Learning Sparse Prototypes for Text Generation
Learning Strategic Network Emergence Games
Learning Strategy-Aware Linear Classifiers
Learning Structured Distributions From Untrusted Batches: Faster and Simpler
Learning the Geometry of Wave-Based Imaging
Learning the Linear Quadratic Regulator from Nonlinear Observations
Learning to Adapt to Evolving Domains
Learning to Approximate a Bregman Divergence
Learning to Decode: Reinforcement Learning for Decoding of Sparse Graph-Based Channel Codes

« prev Page 20/39 next »