Paperlane

no. 10 · Friday 6 November 2026

On the Rate of Gaussian Approximation for Online Linear Regression Problems

Marina Sheshukova, Alain Durmus, Marat Khusainov and Sergey Samsonov

math.OC · v2

Abstract

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.

comments
Published in Statistics (Taylor & Francis, 2026)
journal
Statistics (2026), 1-25
fields
Optimization and Control
pdf ↗ page arXiv:2509.14039 ↗