A Unified Optimism-Agnostic Framework for Linear Bandits over Spherical Action Sets

arXiv:2609.32149 · stat.ML, cs.LG · Submitted 2026-09-26 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Regret — 73× in this paper · explained in 3 episodes
• Thompson Sampling — 20× in this paper
• Upper Confidence Bound — 4× in this paper
• Contextual Bandits — 2× in this paper · explained in 3 episodes
• Regularization — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Minimax Regret — 1× in this paper · explained in 2 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits
• Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier