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
Transferable Graph Optimizers for ML Compilers
Transfer Learning via $\ell_1$ Regularization
Transfer Learning via ℓ1 Regularization
Tree! I am no Tree! I am a low dimensional Hyperbolic Embedding
Triple descent and the two kinds of overfitting: where & why do they appear?
Truncated Linear Regression in High Dimensions
Trust the Model When It Is Confident: Masked Model-based Actor-Critic
Truthful Data Acquisition via Peer Prediction
tspDB: Time Series Predict DB
TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation
UCLID-Net: Single View Reconstruction in Object Space
UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree
UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging
Ultrahyperbolic Representation Learning
Ultra-Low Precision 4-bit Training of Deep Neural Networks
Unbalanced Sobolev Descent
Uncertainty-Aware Learning for Zero-Shot Semantic Segmentation
Uncertainty-aware Self-training for Few-shot Text Classification
Uncertainty Aware Semi-Supervised Learning on Graph Data
Uncertainty Quantification for Inferring Hawkes Networks
Uncovering the Topology of Time-Varying fMRI Data using Cubical Persistence
Understanding and Exploring the Network with Stochastic Architectures
Understanding and Improving Fast Adversarial Training
Understanding Anomaly Detection with Deep Invertible Networks through Hierarchies of Distributions and Features
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks
Understanding Deep Architecture with Reasoning Layer
Understanding Double Descent Requires A Fine-Grained Bias-Variance Decomposition
Understanding Global Feature Contributions With Additive Importance Measures
Understanding Gradient Clipping in Private SGD: A Geometric Perspective
Understanding spiking networks through convex optimization
Understanding the Role of Training Regimes in Continual Learning
Unfolding recurrence by Green's functions for optimized reservoir computing
Unfolding the Alternating Optimization for Blind Super Resolution
Unifying Activation- and Timing-based Learning Rules for Spiking Neural Networks
Universal Domain Adaptation through Self Supervision
Universal Function Approximation on Graphs
Universal guarantees for decision tree induction via a higher-order splitting criterion
Universally Quantized Neural Compression
UnModNet: Learning to Unwrap a Modulo Image for High Dynamic Range Imaging
Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms
Unsupervised Data Augmentation for Consistency Training
Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models
Unsupervised Learning of Dense Visual Representations
Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control
Unsupervised Learning of Object Landmarks via Self-Training Correspondence
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
Unsupervised object-centric video generation and decomposition in 3D
Unsupervised Representation Learning by Invariance Propagation
Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
Unsupervised Sound Separation Using Mixture Invariant Training

« prev Page 37/39 next »