Positive Semidefinite Supermartingales and Randomized Matrix Concentration Inequalities

arXiv:2401.15567v2 Announce Type: replace-cross
Abstract: We present new concentration inequalities for either martingale dependent or exchangeable random symmetric matrices under a variety of tail conditions, encompassing now-standard Chernoff bounds to self-normalized heavy-tailed settings. These inequalities are often randomized in a way that renders them strictly tighter than existing deterministic results in the literature, are typically expressed in the Loewner order, and are sometimes valid at arbitrary data-dependent stopping times. Along the way, we explore the theory of positive semidefinite supermartingales …

abstract arxiv math.fa math.pr math.st matrix positive random standard stat.me stat.ml stat.th them type