Theory

The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions EMNLP 2020 The EM Algorithm gives Sample-Optimality for Learning Mixtures of Well-Separated Gaussians COLT 2020 The Expressive Power of a Class of Normalizing Flow Models AISTATS 2020 The Gambler's Problem and Beyond ICLR 2020 The Generalization-Stability Tradeoff In Neural Network Pruning NeurIPS 2020 The Implicit Bias of Depth: How Incremental Learning Drives Generalization ICLR 2020 The Many Shapley Values for Model Explanation ICML 2020 The phase diagram of approximation rates for deep neural networks NeurIPS 2020 The Smoothed Possibility of Social Choice NeurIPS 2020 The Statistical Complexity of Early-Stopped Mirror Descent NeurIPS 2020 The weight function in the subtree kernel is decisive JMLR 2020 Threshold Treewidth and Hypertree Width IJCAI 2020 Topologically Densified Distributions ICML 2020 Topology of Deep Neural Networks JMLR 2020 Top-Quality Planning: Finding Practically Useful Sets of Best Plans AAAI 2020 To Schedule or not to Schedule: Extracting Task Specific Temporal Entities and Associated Negation Constraints EMNLP 2020 Towards a Combinatorial Characterization of Bounded-Memory Learning NeurIPS 2020 Towards a General Theory of Infinite-Width Limits of Neural Classifiers ICML 2020 Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets ICLR 2020 Towards Certificated Model Robustness Against Weight Perturbations AAAI 2020 Towards Interpretation of Pairwise Learning AAAI 2020 Towards Problem-dependent Optimal Learning Rates NeurIPS 2020 Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations EMNLP 2020 Towards Universal Languages for Tractable Ontology Mediated Query Answering AAAI 2020 Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra JMLR 2020