Learning Theory

Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent AAAI 2024 Towards the Fundamental Limits of Knowledge Transfer over Finite Domains ICLR 2024 Towards Theoretical Understandings of Self-Consuming Generative Models ICML 2024 Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithms ICML 2024 Toward the Evaluation of Large Language Models Considering Score Variance across Instruction Templates EMNLP 2024 Trade-Offs of Diagonal Fisher Information Matrix Estimators NeurIPS 2024 Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis NeurIPS 2024 Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear q^π-Realizability and Concentrability NeurIPS 2024 Transductive Active Learning: Theory and Applications NeurIPS 2024 Transductive Learning is Compact NeurIPS 2024 Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization NeurIPS 2024 Transformers are Minimax Optimal Nonparametric In-Context Learners NeurIPS 2024 Transformers Can Represent n-gram Language Models NAACL 2024 Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot ICML 2024 Transformer verbatim in-context retrieval across time and scale CoNLL 2024 Truncated Variance Reduced Value Iteration NeurIPS 2024 Trustworthy Actionable Perturbations ICML 2024 Truthfulness of Calibration Measures NeurIPS 2024 Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States UAI 2024 Unbiased Faster R-CNN for Single-source Domain Generalized Object Detection CVPR 2024 Understanding and Diagnosing Deep Reinforcement Learning ICML 2024 Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective CVPR 2024 Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory ICLR 2024 Understanding Domain Generalization: A Noise Robustness Perspective ICLR 2024 Understanding Emergent Abilities of Language Models from the Loss Perspective NeurIPS 2024