arXiv:2509.14039 · v2

On the Rate of Gaussian Approximation for Online Linear Regression Problems

首次提交 2025-09-17 22:42

版本更新 2026-11-05 18:57

雷达观测 2026-11-06 12:09

摘要

In this paper, we consider the problem of Gaussian approximation for the online linear regression task. We derive the corresponding rates for the setting of a constant stepsize and study the explicit dependence of the convergence rate on the problem dimension $d$ and quantities related to the design matrix. When the number of iterations $n$ is known in advance, our results yield a normal approximation rate of order $\sqrt{\log{n}/n}$, provided that the sample size $n$ is large enough.

作者备注：Published in Statistics (Taylor & Francis, 2026)

期刊信息：Statistics (2026), 1-25