Learning Theory

Provable Lifelong Learning of Representations AISTATS 2022 Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems NeurIPS 2022 Provably tuning the ElasticNet across instances NeurIPS 2022 Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability AAAI 2022 Quantile regression with ReLU Networks: Estimators and minimax rates JMLR 2022 Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants NeurIPS 2022 Quantum perceptron revisited: Computational-statistical tradeoffs UAI 2022 Queue Up Your Regrets: Achieving the Dynamic Capacity Region of Multiplayer Bandits NeurIPS 2022 Rate-Distortion Theoretic Bounds on Generalization Error for Distributed Learning NeurIPS 2022 Realizable Learning is All You Need COLT 2022 Reconstructing Training Data From Trained Neural Networks NeurIPS 2022 Recovery and Generalization in Over-Realized Dictionary Learning JMLR 2022 Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms NeurIPS 2022 Reducing Flipping Errors in Deep Neural Networks AAAI 2022 Regret Bounds for Information-Directed Reinforcement Learning NeurIPS 2022 Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation ICML 2022 Regret guarantees for model-based reinforcement learning with long-term average constraints UAI 2022 Regret, stability & fairness in matching markets with bandit learners AISTATS 2022 Regularized Modal Regression on Markov-Dependent Observations: A Theoretical Assessment AAAI 2022 Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space NeurIPS 2022 Reinforcement Learning with Logarithmic Regret and Policy Switches NeurIPS 2022 Relational Reasoning via Set Transformers: Provable Efficiency and Applications to MARL NeurIPS 2022 Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum ICLR 2022 Rethinking Attention-Model Explainability through Faithfulness Violation Test ICML 2022 Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022