【论文阅读笔记】NeurIPS2020文章列表Part2

• Online Multitask Learning with Long-Term Memory
• Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• On Reward-Free Reinforcement Learning with Linear Function Approximation
• Robustness of Community Detection to Random Geometric Perturbations
• Learning outside the Black-Box: The pursuit of interpretable models
• Breaking Reversibility Accelerates Langevin Dynamics for Non-Convex Optimization
• Robust large-margin learning in hyperbolic space
• Replica-Exchange Nos’e-Hoover Dynamics for Bayesian Learning on Large Datasets
• Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
• Neural Anisotropy Directions
• Digraph Inception Convolutional Networks
• PAC-Bayesian Bound for the Conditional Value at Risk
• Stochastic Stein Discrepancies
• On the Role of Sparsity and DAG Constraints for Learning Linear DAGs
• Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
• Fair Multiple Decision Making Through Soft Interventions
• Representation Learning for Integrating Multi-domain Outcomes to Optimize Individualized Treatment
• Learning to Play No-Press Diplomacy with Best Response Policy Iteration
• Inverse Learning of Symmetries
• DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling
• Distributed Newton Can Communicate Less and Resist Byzantine Workers
• Efficient Nonmyopic Bayesian Optimization via One-Shot Multi-Step Trees
• Effective Diversity in Population Based Reinforcement Learning
• Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
• Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
• Hybrid Models for Learning to Branch
• WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
• Bi-level Score Matching for Learning Energy-based Latent Variable Models
• Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding
• Decision trees as partitioning machines to characterize their generalization properties
• Learning to Prove Theorems by Learning to Generate Theorems
• 3D Self-Supervised Methods for Medical Imaging
• Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods
• Worst-Case Analysis for Randomly Collected Data
• Truthful Data Acquisition via Peer Prediction
• Learning Robust Decision Policies from Observational Data
• Byzantine Resilient Distributed Multi-Task Learning
• Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting
• Improving model calibration with accuracy versus uncertainty optimization
• The Convolution Exponential and Generalized Sylvester Flows
• An Improved Analysis of Stochastic Gradient Descent with Momentum
• Precise expressions for random projections: Low-rank approximation and randomized Newton
• The MAGICAL Benchmark for Robust Imitation
• X-CAL: Explicit Calibration for Survival Analysis
• Decentralized Accelerated Proximal Gradient Descent
• Making Non-Stochastic Control (Almost) as Easy as Stochastic
• BERT Loses Patience: Fast and Robust Inference with Early Exit
• Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization
• BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
• Regularizing Towards Permutation Invariance In Recurrent Models
• What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes
• Batch normalization provably avoids ranks collapse for randomly initialised deep networks
• Choice Bandits
• What if Neural Networks had SVDs?
• A Matrix Chernoff Bound for Markov Chains and Its Application to Co-occurrence Matrices
• CoMIR: Contrastive Multimodal Image Representation for Registration
• Ensuring Fairness Beyond the Training Data
• How do fair decisions fare in long-term qualification?
• Pre-training via Paraphrasing
• GCN meets GPU: Decoupling “When to Sample” from “How to Sample”
• Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
• All your loss are belong to Bayes
• HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
• Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
• Non-Convex SGD Learns Halfspaces with Adversarial Label Noise
• A Tight Lower Bound and Efficient Reduction for Swap Regret
• DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction
• OTLDA: A Geometry-aware Optimal Transport Approach for Topic Modeling
• Measuring Robustness to Natural Distribution Shifts in Image Classification
• Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference
• RandAugment: Practical Automated Data Augmentation with a Reduced Search Space
• Asymptotic normality and confidence intervals for derivatives of 2-layers neural network in the random features model
• DisARM: An Antithetic Gradient Estimator for Binary Latent Variables
• Variational Inference for Graph Convolutional Networks in the Absence of Graph Data and Adversarial Settings
• Supervised Contrastive Learning
• Learning Optimal Representations with the Decodable Information Bottleneck
• Meta-trained agents implement Bayes-optimal agents
• Learning Agent Representations for Ice Hockey
• Weak Form Generalized Hamiltonian Learning
• Neural Non-Rigid Tracking
• Collegial Ensembles
• ICNet: Intra-saliency Correlation Network for Co-Saliency Detection
• Improved Variational Bayesian Phylogenetic Inference with Normalizing Flows
• Deep Metric Learning with Spherical Embedding