2000 character limit reached
Bernstein-type dimension-free concentration for self-normalised martingales (2507.20982v1)
Published 28 Jul 2025 in math.PR, math.ST, and stat.TH
Abstract: We introduce a dimension-free Bernstein-type tail inequality for self-normalised martingales normalised by their predictable quadratic variation. As applications of our result, we propose solutions to the recent open problems posed by Mussi et al. (2024), providing computationally efficient confidence sequences for logistic regression with adaptively chosen RKHS-valued covariates, and establishing instance-adaptive regret bounds in the corresponding kernelised bandit setting.