Learning Theory

Towards Context-Agnostic Learning Using Synthetic Data NeurIPS 2021 Towards Extracting Graph Neural Network Models via Prediction Queries (Student Abstract) AAAI 2021 Towards Instance-Optimal Offline Reinforcement Learning with Pessimism NeurIPS 2021 Towards Lower Bounds on the Depth of ReLU Neural Networks NeurIPS 2021 Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning ICLR 2021 Towards Sharper Generalization Bounds for Structured Prediction NeurIPS 2021 Towards Tight Bounds on the Sample Complexity of Average-reward MDPs ICML 2021 Towards Tight Communication Lower Bounds for Distributed Optimisation NeurIPS 2021 Towards Understanding Learning in Neural Networks with Linear Teachers ICML 2021 Towards Understanding the Spectral Bias of Deep Learning IJCAI 2021 Tracking Regret Bounds for Online Submodular Optimization AISTATS 2021 Tractable contextual bandits beyond realizability AISTATS 2021 Training deep residual networks for uniform approximation guarantees L4DC 2021 Training Neural Networks is ER-complete NeurIPS 2021 Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction ACL 2021 Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits JMLR 2021 Turing Completeness of Bounded-Precision Recurrent Neural Networks NeurIPS 2021 Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution NeurIPS 2021 UCB Momentum Q-learning: Correcting the bias without forgetting ICML 2021 Understanding Bandits with Graph Feedback NeurIPS 2021 Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron ACML 2021 Understanding self-supervised learning dynamics without contrastive pairs ICML 2021 Understanding the Behaviour of Contrastive Loss CVPR 2021 Understanding the Effect of Bias in Deep Anomaly Detection IJCAI 2021 Understanding the Generalization Benefit of Model Invariance from a Data Perspective NeurIPS 2021