A line search framework with restarting for noisy optimization problems
Abstract
Nonlinear optimization methods are typically iterative and make use of gradient information to determine a direction of improvement and function information to effectively check for progress. When this information is corrupted by noise, designing a convergent and practical algorithmic process becomes challenging, as care must be taken to avoid taking bad steps due to erroneous information. For this reason, simple gradient-based schemes have been quite popular, despite being outperformed by more advanced techniques in the noiseless setting. In this paper, we propose a general algorithmic framework based on line search that is endowed with iteration and evaluation complexity guarantees even in a noisy setting. These guarantees are obtained as a result of a restarting condition, that monitors desirable properties for the steps taken at each iteration and can be checked even in the presence of noise. Experiments using a nonlinear conjugate gradient variant and a quasi-Newton variant illustrate that restarting can be performed without compromising practical efficiency and robustness.
Cite
@article{arxiv.2506.03358,
title = {A line search framework with restarting for noisy optimization problems},
author = {Albert S. Berahas and Michael J. O'Neill and Clément W. Royer},
journal= {arXiv preprint arXiv:2506.03358},
year = {2025}
}