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
Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization
Generalized Boosting
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection
Generalized Hindsight for Reinforcement Learning
Generalized Independent Noise Condition for Estimating Latent Variable Causal Graphs
Generalized Leverage Score Sampling for Neural Networks
General Transportability of Soft Interventions: Completeness Results
Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning
Generating Correct Answers for Progressive Matrices Intelligence Tests
Generative 3D Part Assembly via Dynamic Graph Learning
Generative causal explanations of black-box classifiers
Generative Neurosymbolic Machines
Generative View Synthesis: From Single-view Semantics to Novel-view Images
Geometric All-way Boolean Tensor Decomposition
Geometric Dataset Distances via Optimal Transport
Geometric Exploration for Online Control
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
Gibbs Sampling with People
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems
Global Convergence of Deep Networks with One Wide Layer Followed by Pyramidal Topology
Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Search
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data
GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
Goal-directed Generation of Discrete Structures with Conditional Generative Models
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
GPS-Net: Graph-based Photometric Stereo Network
GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification
GradAug: A New Regularization Method for Deep Neural Networks
Gradient Boosted Normalizing Flows
Gradient-EM Bayesian Meta-Learning
Gradient Estimation with Stochastic Softmax Tricks
Gradient Regularized V-Learning for Dynamic Treatment Regimes
Gradient Surgery for Multi-Task Learning
Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning
GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
Graph Contrastive Learning with Augmentations
Graph Cross Networks with Vertex Infomax Pooling
Graph Geometry Interaction Learning
Graph Information Bottleneck
Graph Meta Learning via Local Subgraphs
Graphon Neural Networks and the Transferability of Graph Neural Networks
Graph Policy Network for Transferable Active Learning on Graphs
Graph Random Neural Networks for Semi-Supervised Learning on Graphs
Graph Stochastic Neural Networks for Semi-supervised Learning
Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Grasps
GreedyFool: Distortion-Aware Sparse Adversarial Attack
Greedy inference with structure-exploiting lazy maps
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough

« prev Page 15/39 next »