Saved in:
Bibliographic Details
Main Authors: Xu, Lei, Yi, Xinlei, Sun, Jiayue, Shi, Yang, Johansson, Karl H., Yang, Tao
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2207.08106
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909515390124032
author Xu, Lei
Yi, Xinlei
Sun, Jiayue
Shi, Yang
Johansson, Karl H.
Yang, Tao
author_facet Xu, Lei
Yi, Xinlei
Sun, Jiayue
Shi, Yang
Johansson, Karl H.
Yang, Tao
contents This paper considers distributed optimization for minimizing the average of local nonconvex cost functions, by using local information exchange over undirected communication networks. To reduce the required communication capacity, we introduce an encoder--decoder scheme. By integrating them with distributed gradient tracking and proportional integral algorithms, respectively, we then propose two quantized distributed nonconvex optimization algorithms. Assuming the global cost function satisfies the Polyak--Łojasiewicz condition, which does not require the global cost function to be convex and the global minimizer is not necessarily unique, we show that our proposed algorithms linearly converge to a global optimal point and that larger quantization level leads to faster convergence speed. Moreover, we show that a low data rate is sufficient to guarantee linear convergence when the algorithm parameters are properly chosen. The theoretical results are illustrated by numerical examples.
format Preprint
id arxiv_https___arxiv_org_abs_2207_08106
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Quantized Distributed Nonconvex Optimization Algorithms with Linear Convergence under the Polyak--$Ł$ojasiewicz Condition
Xu, Lei
Yi, Xinlei
Sun, Jiayue
Shi, Yang
Johansson, Karl H.
Yang, Tao
Optimization and Control
This paper considers distributed optimization for minimizing the average of local nonconvex cost functions, by using local information exchange over undirected communication networks. To reduce the required communication capacity, we introduce an encoder--decoder scheme. By integrating them with distributed gradient tracking and proportional integral algorithms, respectively, we then propose two quantized distributed nonconvex optimization algorithms. Assuming the global cost function satisfies the Polyak--Łojasiewicz condition, which does not require the global cost function to be convex and the global minimizer is not necessarily unique, we show that our proposed algorithms linearly converge to a global optimal point and that larger quantization level leads to faster convergence speed. Moreover, we show that a low data rate is sufficient to guarantee linear convergence when the algorithm parameters are properly chosen. The theoretical results are illustrated by numerical examples.
title Quantized Distributed Nonconvex Optimization Algorithms with Linear Convergence under the Polyak--$Ł$ojasiewicz Condition
topic Optimization and Control
url https://arxiv.org/abs/2207.08106