Learning Theory

Streaming k-PCA: Efficient guarantees for Oja’s algorithm, beyond rank-one updates COLT 2021 Student-Teacher Learning From Clean Inputs to Noisy Inputs CVPR 2021 Subgroup Generalization and Fairness of Graph Neural Networks NeurIPS 2021 Suboptimal coverings for continuous spaces of control tasks L4DC 2021 Subquadratic Overparameterization for Shallow Neural Networks NeurIPS 2021 Supervising the Transfer of Reasoning Patterns in VQA NeurIPS 2021 Support Recovery of Sparse Signals from a Mixture of Linear Measurements NeurIPS 2021 Surrogate Regret Bounds for Polyhedral Losses NeurIPS 2021 Systematic Generalization on gSCAN: What is Nearly Solved and What is Next? EMNLP 2021 Task similarity aware meta learning: theory-inspired improvement on MAML UAI 2021 Taxonomizing local versus global structure in neural network loss landscapes NeurIPS 2021 Taxonomy Completion via Triplet Matching Network AAAI 2021 Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm NeurIPS 2021 Tensor Programs IIb: Architectural Universality Of Neural Tangent Kernel Training Dynamics ICML 2021 Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning ICML 2021 TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models ACL 2021 The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition NeurIPS 2021 The Complexity of Bayesian Network Learning: Revisiting the Superstructure NeurIPS 2021 The Complexity of Sparse Tensor PCA NeurIPS 2021 The Connection Between Approximation, Depth Separation and Learnability in Neural Networks COLT 2021 The curious case of adversarially robust models: More data can help, double descend, or hurt generalization UAI 2021 The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers NeurIPS 2021 The future is log-Gaussian: ResNets and their infinite-depth-and-width limit at initialization NeurIPS 2021 The Heavy-Tail Phenomenon in SGD ICML 2021 The Implicit Bias of Minima Stability: A View from Function Space NeurIPS 2021