cs.LG, math.ST, stat.ML, stat.TH

Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression

arXiv:2605.01628v1 Announce Type: new
Abstract: Self-normalized martingale inequalities lie at the heart of confidence ellipsoids for online least squares and, more broadly, many bandit and reinforcement-learning results. Yet existing vector and scala…