Learning Theory

Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models ICLR 2023 Benign Overfitting in Deep Neural Networks under Lazy Training ICML 2023 Benign Overfitting in Linear Classifiers and Leaky ReLU Networks from KKT Conditions for Margin Maximization COLT 2023 Benign overfitting in ridge regression JMLR 2023 Benign Overfitting in Two-layer ReLU Convolutional Neural Networks ICML 2023 Benign Overfitting of Constant-Stepsize SGD for Linear Regression JMLR 2023 Benign overfitting of non-smooth neural networks beyond lazy training AISTATS 2023 Best arm identification in rare events UAI 2023 Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds COLT 2023 Beyond Average Return in Markov Decision Processes NeurIPS 2023 Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD ICLR 2023 Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time NeurIPS 2023 Beyond Parallel Pancakes: Quasi-Polynomial Time Guarantees for Non-Spherical Gaussian Mixtures COLT 2023 Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models ACL 2023 Beyond Strict Competition: Approximate Convergence of Multi-agent Q-Learning Dynamics IJCAI 2023 Binary Classification with Confidence Difference NeurIPS 2023 B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding ICML 2023 BLM-AgrF: A New French Benchmark to Investigate Generalization of Agreement in Neural Networks EACL 2023 Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff NeurIPS 2023 Bounding Evidence and Estimating Log-Likelihood in VAE AISTATS 2023 Bounding training data reconstruction in DP-SGD NeurIPS 2023 Breaking a Classical Barrier for Classifying Arbitrary Test Examples in the Quantum Model AISTATS 2023 Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation COLT 2023 Bridging RL Theory and Practice with the Effective Horizon NeurIPS 2023 Can LMs Generalize to Future Data? An Empirical Analysis on Text Summarization EMNLP 2023