Moderate Deviation Principle for a Stochastic Approximation Process
Probability
2026-05-11 v1
Abstract
In this paper, we investigate a stochastic approximation procedure taking values in . The process is adapted to a filtration and satisfies the recursion , where , is a function and is a sequence of bounded martingale differences adapted to the filtration . We establish the moderate deviation principle for the stochastic process . As auxiliary results, we also obtain the exponential inequality for and the moderate deviation principle for weighted sums of bounded martingale differences.
Cite
@article{arxiv.2605.07369,
title = {Moderate Deviation Principle for a Stochastic Approximation Process},
author = {Jianan Shi and Qing Yin and Yu Miao},
journal= {arXiv preprint arXiv:2605.07369},
year = {2026}
}
Comments
22 pages, 0 figures