Salvato in:
Dettagli Bibliografici
Autori principali: Dai, Hongsheng, Fan, Xiequan, Lu, Jianya
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.22047
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
Sommario:
  • In this paper, we study the self-normalized Cramér-type moderate deviation of the empirical measure of the stochastic gradient Langevin dynamics (SGLD). Consequently, we also derive the Berry-Esseen bound for SGLD. Our approach is by constructing a stochastic differential equation (SDE) to approximate the SGLD and then applying Stein's method as developed in [9,19], to decompose the empirical measure into a martingale difference series sum and a negligible remainder term.