learning theory

Learning with Explanation Constraints NeurIPS 2023 Machines of Finite Depth: Towards a Formalization of Neural Networks AAAI 2023 Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off NeurIPS 2023 Most Neural Networks Are Almost Learnable NeurIPS 2023 Nearly Optimal Bounds for Cyclic Forgetting NeurIPS 2023 Near-Optimal $Φ$-Regret Learning in Extensive-Form Games ICML 2023 Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise NeurIPS 2023 Near-optimal learning with average Hölder smoothness NeurIPS 2023 “No Free Lunch” in Neural Architectures? A Joint Analysis of Expressivity, Convergence, and Generalization AutoML 2023 On Batch Teaching Without Collusion JMLR 2023 On Masked Pre-training and the Marginal Likelihood NeurIPS 2023 On the Capacity Limits of Privileged ERM AISTATS 2023 On the Complexity of PAC Learning in Hilbert Spaces AAAI 2023 On the Consistency Rate of Decision Tree Learning Algorithms AISTATS 2023 On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis NeurIPS 2023 On the Learnability of Multilabel Ranking NeurIPS 2023 On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples AAAI 2023 On the Variance, Admissibility, and Stability of Empirical Risk Minimization NeurIPS 2023 Open problem: log(n) factor in "Local Glivenko-Cantelli" COLT 2023 Optimal Excess Risk Bounds for Empirical Risk Minimization on p-Norm Linear Regression NeurIPS 2023 Progress measures for grokking via mechanistic interpretability ICLR 2023 Provable Guarantees for Neural Networks via Gradient Feature Learning NeurIPS 2023 Quantitative Universal Approximation Bounds for Deep Belief Networks ICML 2023 Reliable learning in challenging environments NeurIPS 2023 Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity NeurIPS 2023