Randomized gradient-free methods in convex optimization
Optimization and Control
2024-09-17 v3
Abstract
This review presents modern gradient-free methods to solve convex optimization problems. By gradient-free methods, we mean those that use only (noisy) realizations of the objective value. We are motivated by various applications where gradient information is prohibitively expensive or even unavailable. We mainly focus on three criteria: oracle complexity, iteration complexity, and the maximum permissible noise level.
Cite
@article{arxiv.2211.13566,
title = {Randomized gradient-free methods in convex optimization},
author = {Alexander Gasnikov and Darina Dvinskikh and Pavel Dvurechensky and Eduard Gorbunov and Aleksander Beznosikov and Aleksandr Lobanov},
journal= {arXiv preprint arXiv:2211.13566},
year = {2024}
}
Comments
Survey paper; 9 pages