Learning Theory

Tight Sample Complexity of Transformers COLT 2026 TimeMachine-bench: A Benchmark for Evaluating Model Capabilities in Repository-Level Migration Tasks EACL 2026 Towards a Rigorous Understanding of the Population Dynamics of the NSGA-III: Tight Runtime Bounds AAAI 2026 Toward Simultaneously Optimal Regret in U-Calibration COLT 2026 Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs AAAI 2026 Towards Understanding In-Context Learning of Transformers Under Non-I.I.D. Scenarios AAAI 2026 TRACE: Trajectory-based Activation Change Estimation for Task-specific Data Selection AAAI 2026 Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities AAAI 2026 Unified Framework of Distributional Regret in Multi-Armed Bandits and Reinforcement Learning COLT 2026 Unified Structural Factors for Transfer Learning Generalization with PAC-Bayesian Guarantees AAAI 2026 Uniform Laws of Large Numbers in Product Spaces COLT 2026 Unlearning in Cross-Modal Retrieval via Prior-Prototype Guided Partitioned Dampening AAAI 2026 Variation-Bounded Loss for Noise-Tolerant Learning AAAI 2026 VerifyBench: A Systematic Benchmark for Evaluating Reasoning Verifiers Across Domains AAAI 2026 Wasserstein Policy Learning for Distributional Outcomes COLT 2026 When and How Often is Weighted Majority Vote Optimal Under Log Loss? UAI 2026 When Can We Learn from Noisy Logical Data? Parameterized Complexity of Approximate Concept Fitting in Description Logics UAI 2026 Worst-case Error Bounds for Online Learning of Smooth Functions COLT 2026 φ-Update: A Class of Policy Update Methods with Policy Convergence Guarantee ICLR 2025 A Characterization of List Regression ALT 2025 A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks ICML 2025 A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networks AISTATS 2025 Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss ICML 2025 Active Bipartite Ranking with Smooth Posterior Distributions AISTATS 2025 Active Learning for Continual Learning: Keeping the Past Alive in the Present ICLR 2025