Bernstein-type dimension-free concentration for self-normalised martingales

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.