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
LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration
Low Distortion Block-Resampling with Spatially Stochastic Networks
Lower Bounds and Optimal Algorithms for Personalized Federated Learning
Make One-Shot Video Object Segmentation Efficient Again
Making Non-Stochastic Control (Almost) as Easy as Stochastic
Manifold GPLVMs for discovering non-Euclidean latent structure in neural data
Manifold structure in graph embeddings
Marginal Utility for Planning in Continuous or Large Discrete Action Spaces
Margins are Insufficient for Explaining Gradient Boosting
Markovian Score Climbing: Variational Inference with KL(p||q)
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning
Matérn Gaussian Processes on Riemannian Manifolds
Matrix Completion with Hierarchical Graph Side Information
Matrix Completion with Quantified Uncertainty through Low Rank Gaussian Copula
Matrix Inference and Estimation in Multi-Layer Models
Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
MCUNet: Tiny Deep Learning on IoT Devices
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
Measuring Robustness to Natural Distribution Shifts in Image Classification
Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark
Measuring Systematic Generalization in Neural Proof Generation with Transformers
Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards
Memory-Efficient Learning of Stable Linear Dynamical Systems for Prediction and Control
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
MeshSDF: Differentiable Iso-Surface Extraction
Meta-Consolidation for Continual Learning
Meta-Gradient Reinforcement Learning with an Objective Discovered Online
Meta-learning from Tasks with Heterogeneous Attribute Spaces
Meta-Learning Requires Meta-Augmentation
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
Meta-Learning through Hebbian Plasticity in Random Networks
Meta-Learning with Adaptive Hyperparameters
Meta-Neighborhoods
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPoison: Practical General-purpose Clean-label Data Poisoning
MetaSDF: Meta-Learning Signed Distance Functions
Meta-trained agents implement Bayes-optimal agents
Methods and Analysis of The First Competition in Predicting Generalization of Deep Learning
Metric-Free Individual Fairness in Online Learning
Minibatch Stochastic Approximate Proximal Point Methods
Minibatch vs Local SGD for Heterogeneous Distributed Learning
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
Minimax Bounds for Generalized Linear Models
Minimax Classification with 0-1 Loss and Performance Guarantees
Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons
Minimax Estimation of Conditional Moment Models
Minimax Lower Bounds for Transfer Learning with Linear and One-hidden Layer Neural Networks
Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects
Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization

« prev Page 22/39 next »