Learning Theory

Sparse Nonparametric Contextual Bandits ALT 2026 Specification-Guided Reinforcement Learning AAAI 2026 Stabilizing Policy Gradient Methods via Reward Profiling AAAI 2026 Stable algorithms Lower Bounds for Estimation from MMSE Discontinuities: Extended Abstract COLT 2026 Statistical Learning from Attribution Sets COLT 2026 Statistical Learning Theory for Distributional Classification AAAI 2026 Statistical Learning Theory for Neural Operators JMLR 2026 Steering diffusion models with quadratic rewards: a fine-grained analysis COLT 2026 Stochastic Decentralized Optimization of Non-Smooth Convex and Convex-Concave Problems over Time-Varying Networks AAAI 2026 Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent JMLR 2026 Stochastic Gradient Methods: Bias, Stability and Generalization JMLR 2026 Surprisal and Metaphor Novelty Judgments: Moderate Correlations and Divergent Scaling Effects Revealed by Corpus-Based and Synthetic Datasets EACL 2026 Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits COLT 2026 Testing for a Hidden Geometry in Random Graphs COLT 2026 Testing Noise Assumptions of Learning Algorithms COLT 2026 The Monotonicity of the Franz–Parisi Potential Is Equivalent to Low-Degree MMSE Lower Bounds: Extended Abstract COLT 2026 Theoretical and Empirical Analysis of Lehmer Codes to Search Permutation Spaces with Evolutionary Algorithms AAAI 2026 Theoretical Guarantees for Domain Adaptation with Hierarchical Optimal Transport (Abstract Reprint) AAAI 2026 The Role of Contextual Information in Best Arm Identification JMLR 2026 The Sample Complexity of Multiclass and Sparse Contextual Bandits COLT 2026 The Sample Complexity of Parameter-Free Stochastic Convex Optimization JMLR 2026 The Search for Stability: Learning Dynamics of Strategic Publishers with Initial Documents (Abstract Reprint) AAAI 2026 Three Types of Calibration using Properties and their Semantic and Formal Relationships JMLR 2026 Tight Bounds for Logistic Regression with Large Stepsize Gradient Descent in Low Dimension COLT 2026 Tight list replicability bounds via a novel sphere covering theorem COLT 2026