Communication Compression for Distributed Nonconvex Optimization
IEEE Transactions on Automatic Control · 2023-09 · 68 (9) · 5477-5492
DOI: 10.1109/tac.2022.3225515 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2023-09. Verfasst von Xinlei Yi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Knut och Alice Wallenbergs Stiftelse, Swedish Foundation for Strategic Research, Vetenskapsrådet.
Abstract (Originalsprache)
In this article, we consider distributed nonconvex optimization with the cost functions being distributed over agents. Noting that information compression is a key tool to reduce the heavy communication load for distributed algorithms as agents iteratively communicate with neighbors, we propose three distributed primal–dual algorithms with compressed communication. The first two algorithms are applicable to a general class of compressors with bounded relative compression error and the third algorithm is suitable for two general classes of compressors with bounded absolute compression error. We show that the proposed distributed algorithms with compressed communication have comparable convergence properties as state-of-the-art algorithms with exact communication. Specifically, we show that they can find first-order stationary points with sublinear convergence rate $\mathcal {O}(1/T)$ when each local cost function is smooth, where $T$ is the total number of iterations, and find global optima with linear convergence rate under an additional condition that the global cost function satisfies the Polyak–Łojasiewicz condition. Numerical simulations are provided to illustrate the effectiveness of the theoretical results.
Förderung
- Knut och Alice Wallenbergs Stiftelse
- Swedish Foundation for Strategic Research
- Vetenskapsrådet
- National Natural Science Foundation of China
- 2020 Science and Technology Major Project of Liaoning Province
Zitieren
APA
Yi, X., Zhang, S., Yang, T., Chai, T., & Johansson, K. H. (2023). Communication Compression for Distributed Nonconvex Optimization. IEEE Transactions on Automatic Control, 68(9), 5477-5492. https://doi.org/10.1109/tac.2022.3225515
Vancouver
Yi X, Zhang S, Yang T, Chai T, Johansson KH. Communication Compression for Distributed Nonconvex Optimization. IEEE Transactions on Automatic Control. 2023;68(9):5477-5492. doi:10.1109/tac.2022.3225515
BibTeX
@article{Yi2023,
author = {Yi, Xinlei and Zhang, Shengjun and Yang, Tao and Chai, Tianyou and Johansson, Karl Henrik},
title = {Communication Compression for Distributed Nonconvex Optimization},
journal = {IEEE Transactions on Automatic Control},
year = {2023},
volume = {68},
number = {9},
pages = {5477--5492},
doi = {10.1109/tac.2022.3225515}
}
EUVIMED