Time-uniform concentration bounds for iterative algorithms
Abstract
We develop a new framework for deriving time-uniform concentration bounds for the output of stochastic sequential algorithms satisfying certain recursive inequalities akin to those defining the almost-supermartingale processes introduced by \cite{robbins1971convergence}. Our approach is of wide applicability, and can be deployed in settings in which exponential supermartingale processes, required by prevailing methodologies for anytime-valid concentration inequalities, are not readily available. Our results can be viewed as quantitative versions of the classical Robbins-Siegmund Lemma. We demonstrate the effectiveness of our method by providing new and optimal time-uniform concentration bounds for Oja's algorithm for streaming PCA, stochastic gradient descent, and stochastic approximations.
Cite
@article{arxiv.2511.18273,
title = {Time-uniform concentration bounds for iterative algorithms},
author = {Tuan Pham and Alessandro Rinaldo and Purnamrita Sarkar},
journal= {arXiv preprint arXiv:2511.18273},
year = {2025}
}