learning theory

Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views? ICLR 2022 DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS ICLR 2022 Exact Learning of Preference Structure: Single-peaked Preferences and Beyond ICML 2022 Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks NeurIPS 2022 Generalization Bounds for Gradient Methods via Discrete and Continuous Prior NeurIPS 2022 Hardness of Learning a Single Neuron with Adversarial Label Noise AISTATS 2022 Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks NeurIPS 2022 Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NeurIPS 2022 High Probability Generalization Bounds with Fast Rates for Minimax Problems ICLR 2022 Identifiability Conditions for Domain Adaptation ICML 2022 Investigating Generalization by Controlling Normalized Margin ICML 2022 KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints JMLR 2022 Learning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and the Explanations AAAI 2022 LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL ICLR 2022 Linear Label Ranking with Bounded Noise NeurIPS 2022 Local Identifiability of Deep ReLU Neural Networks: the Theory NeurIPS 2022 Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians ALT 2022 Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs ICLR 2022 Multi-Class H-Consistency Bounds NeurIPS 2022 Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise COLT 2022 On Leave-One-Out Conditional Mutual Information For Generalization NeurIPS 2022 Online PAC-Bayes Learning NeurIPS 2022 On Numerical Integration in Neural Ordinary Differential Equations ICML 2022 On Robust Multiclass Learnability NeurIPS 2022 On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model NeurIPS 2022