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
Bandit Linear Control
BanditPAM: Almost Linear Time k-Medoids Clustering via Multi-Armed Bandits
Bandit Samplers for Training Graph Neural Networks
Barking up the right tree: an approach to search over molecule synthesis DAGs
Batched Coarse Ranking in Multi-Armed Bandits
Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks
Batch normalization provably avoids ranks collapse for randomly initialised deep networks
Baxter Permutation Process
Bayes Consistency vs. H-Consistency: The Interplay between Surrogate Loss Functions and the Scoring Function Class
Bayesian Attention Modules
Bayesian Bits: Unifying Quantization and Pruning
Bayesian Causal Structural Learning with Zero-Inflated Poisson Bayesian Networks
Bayesian Deep Ensembles via the Neural Tangent Kernel
Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods
Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
Bayesian Multi-type Mean Field Multi-agent Imitation Learning
Bayesian Optimization for Iterative Learning
Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020
Bayesian Optimization of Risk Measures
Bayesian Probabilistic Numerical Integration with Tree-Based Models
Bayesian Pseudocoresets
Bayesian Robust Optimization for Imitation Learning
BayReL: Bayesian Relational Learning for Multi-omics Data Integration
Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information
Belief Propagation Neural Networks
Benchmarking Deep Inverse Models over time, and the Neural-Adjoint method
Benchmarking Deep Learning Interpretability in Time Series Predictions
BERT Loses Patience: Fast and Robust Inference with Early Exit
Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs
Beta R-CNN: Looking into Pedestrian Detection from Another Perspective
Better Full-Matrix Regret via Parameter-Free Online Learning
Better Set Representations For Relational Reasoning
Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
Beyond Lazy Training for Over-parameterized Tensor Decomposition
Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examples
Beyond the Mean-Field: Structured Deep Gaussian Processes Improve the Predictive Uncertainties
Biased Stochastic First-Order Methods for Conditional Stochastic Optimization and Applications in Meta Learning
Bias no more: high-probability data-dependent regret bounds for adversarial bandits and MDPs
Bidirectional Convolutional Poisson Gamma Dynamical Systems
Big Bird: Transformers for Longer Sequences
Big Self-Supervised Models are Strong Semi-Supervised Learners
Bi-level Score Matching for Learning Energy-based Latent Variable Models
Biological credit assignment through dynamic inversion of feedforward networks
Biologically Inspired Mechanisms for Adversarial Robustness
Black-Box Certification with Randomized Smoothing: A Functional Optimization Based Framework
Black-Box Optimization with Local Generative Surrogates
Black-Box Ripper: Copying black-box models using generative evolutionary algorithms
Blind Video Temporal Consistency via Deep Video Prior

« prev Page 5/39 next »