English

One-Point Feedback for Composite Optimization with Applications to Distributed and Federated Learning

Optimization and Control 2025-07-23 v3 Distributed, Parallel, and Cluster Computing

Abstract

This work is devoted to solving the composite optimization problem with the mixture oracle: for the smooth part of the problem, we have access to the gradient, and for the non-smooth part, only the one-point zero-order oracle is available. For such a setup, we present a new method based on the sliding algorithm. Our method allows to separate the oracle complexities and to compute the gradient for one of the functions as rarely as possible. The paper also presents the applicability of our new method to the problems of distributed optimization and federated learning. Experimental results confirm the theory.

Keywords

Cite

@article{arxiv.2107.05951,
  title  = {One-Point Feedback for Composite Optimization with Applications to Distributed and Federated Learning},
  author = {Aleksandr Beznosikov and Ivan Stepanov and Artyom Voronov and Alexander Gasnikov},
  journal= {arXiv preprint arXiv:2107.05951},
  year   = {2025}
}

Comments

New in v3: completely new text of the paper; 33 pages, 1 figure, 2 tables, 1 algorithm

R2 v1 2026-06-24T04:08:35.064Z