Online Learning

Adaptive Learning Rates with Surrogate Probability for Follow-the-Perturbed-Leader COLT 2026 Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization COLT 2026 Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning L4DC 2026 Adaptive Weighted Averaging COLT 2026 Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret COLT 2026 Almost sure null bankruptcy of testing-by-betting strategies COLT 2026 Ambiguous Online Learning COLT 2026 An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning CVPR 2026 A simple, optimal and efficient algorithm for online exp-concave optimization COLT 2026 Bandit Learning for Online Scheduling with Immediate Decision UAI 2026 Blackwell Approachability and Gradient Equilibrium are Equivalent COLT 2026 Calibeating Made Simple COLT 2026 Calibration-Aware Online Adaptation under Label Shift UAI 2026 Characterizing Online and Private Learnability under Distributional Constraints via Generalized Smoothness COLT 2026 Conformal Online Model Aggregation UAI 2026 Defensive Generation COLT 2026 Discriminative Feature Feedback with General Teacher Classes ALT 2026 Distribution-Free Sequential Prediction with Abstentions COLT 2026 Dynamic Regret in Outlier-Oblivious Online Optimization using Nonconvex Robust Losses UAI 2026 Eventually LIL Regret: Almost Sure $\ln\ln T$ Regret for a sub-Gaussian Mixture on Unbounded Data ALT 2026 Expert Advice with Costly Observations UAI 2026 Fast Best-in-Class Regret for Contextual Bandits UAI 2026 Foundations of Safe Online Reinforcement Learning in the Linear Quadratic Regulator: √T-Regret L4DC 2026 Gradient-Variation Regret Bounds for Unconstrained Online Learning COLT 2026 Improving online FDR procedures via online analogs of e-closure and compound e-values UAI 2026