learning theory

Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization NeurIPS 2023 Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models NeurIPS 2023 SQ Lower Bounds for Learning Mixtures of Linear Classifiers NeurIPS 2023 Stability-Based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning AAAI 2023 Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks NeurIPS 2023 The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks ICLR 2023 The Bayesian Stability Zoo NeurIPS 2023 The Influence of Dimensions on the Complexity of Computing Decision Trees AAAI 2023 Theory on Forgetting and Generalization of Continual Learning ICML 2023 Tighter Information-Theoretic Generalization Bounds from Supersamples ICML 2023 Tighter PAC-Bayes Generalisation Bounds by Leveraging Example Difficulty AISTATS 2023 Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games NeurIPS 2023 Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression NeurIPS 2023 Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NeurIPS 2023 Tree Learning: Optimal Sample Complexity and Algorithms AAAI 2023 Understanding Backdoor Attacks through the Adaptability Hypothesis ICML 2023 Understanding Train-Validation Split in Meta-Learning with Neural Networks ICLR 2023 Uniform Convergence with Square-Root Lipschitz Loss NeurIPS 2023 Active Learning Polynomial Threshold Functions NeurIPS 2022 A Fourier Approach to Mixture Learning NeurIPS 2022 A general approximation lower bound in L^p norm, with applications to feed-forward neural networks NeurIPS 2022 An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn ICML 2022 A spectral-based analysis of the separation between two-layer neural networks and linear methods JMLR 2022 A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features ICLR 2022 A universally consistent learning rule with a universally monotone error JMLR 2022