Learning Theory

Refined Risk Bounds for Unbounded Losses via Transductive Priors JMLR 2026 Regularized Robustly Reliable Learners ALT 2026 Relative Information Gain and Gaussian Process Regression ALT 2026 Relatively Smart: A New Approach for Instance-Optimal Learning COLT 2026 Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message Passing Limit AAAI 2026 Resolving Predictive Multiplicity for the Rashomon Set AAAI 2026 Revealing Redundant Syntax in Large Language Models through Multi-Hop Dependency Paths EACL 2026 Revisiting Generalization Across Difficulty Levels: It’s Not So Easy EACL 2026 Robust Causal Discovery Under Imperfect Structural Constraints AAAI 2026 Robust Decentralized Multi-armed Bandits: From Corruption-Resilience to Byzantine-Resilience AAAI 2026 RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets EACL 2026 Sample-Efficient Omniprediction for Proper Losses COLT 2026 Sample-Near-Optimal Agnostic Boosting with Improved Running Time ALT 2026 Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size? AAAI 2026 Scaling Law for Large Wireless Models AAAI 2026 Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translation AAAI 2026 Second-Order Bounds for $[0,1]$-Valued Regression via Betting Loss COLT 2026 Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression COLT 2026 Semi-supervised Domain Adaptation via Mutual Alignment through Joint Error WACV 2026 Separating Oblivious and Adaptive Models of Variable Selection (Extended Abstract) COLT 2026 Simultaneous Blackwell Approachability and Applications to Multiclass Omniprediction COLT 2026 Single-Network Asymptotics for Causal Inference with Partial Network Data UAI 2026 Sleep-Like Replay Reduces Loss-Landscape Sharpness to Improve Generalization (Student Abstract) AAAI 2026 SoMe: A Realistic Benchmark for LLM-based Social Media Agents AAAI 2026 Space-Efficient Language Generation in the Limit COLT 2026