In this paper we study a generalization of distributed conditional gradient method to time-varying network architectures. We theoretically analyze convergence properties of the algorithm and provide numerical experiments. The time-varying network is modeled as a deterministic of a stochastic sequence of graphs.
@article{arxiv.2307.10978,
title = {Decentralized conditional gradient method over time-varying graphs},
author = {Roman Vedernikov and Alexander Rogozin and Alexander Gasnikov},
journal= {arXiv preprint arXiv:2307.10978},
year = {2023}
}