learning theory

Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions AISTATS 2021 Generalization Guarantee of SGD for Pairwise Learning NeurIPS 2021 Generalization in Portfolio-Based Algorithm Selection AAAI 2021 Identification of the Generalized Condorcet Winner in Multi-dueling Bandits NeurIPS 2021 Impact of Representation Learning in Linear Bandits ICLR 2021 Information-theoretic generalization bounds for black-box learning algorithms NeurIPS 2021 Learning a mixture of two subspaces over finite fields ALT 2021 Learning and certification under instance-targeted poisoning UAI 2021 Learning and testing junta distributions with sub cube conditioning COLT 2021 Learning Theory Can (Sometimes) Explain Generalisation in Graph Neural Networks NeurIPS 2021 Limitations of Post-Hoc Feature Alignment for Robustness CVPR 2021 Littlestone Classes are Privately Online Learnable NeurIPS 2021 Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries ICML 2021 On the Cryptographic Hardness of Learning Single Periodic Neurons NeurIPS 2021 On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexity AISTATS 2021 On the Power of Differentiable Learning versus PAC and SQ Learning NeurIPS 2021 Optimal prediction of Markov chains with and without spectral gap NeurIPS 2021 Perturbation Theory for the Information Bottleneck NeurIPS 2021 Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers NeurIPS 2021 Prediction with Finitely many Errors Almost Surely AISTATS 2021 Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping ICML 2021 RATT: Leveraging Unlabeled Data to Guarantee Generalization ICML 2021 Rissanen Data Analysis: Examining Dataset Characteristics via Description Length ICML 2021 Robust Learning under Strong Noise via SQs AISTATS 2021 Sample Complexity of Robust Linear Classification on Separated Data ICML 2021