Enhancing Convergence of Decentralized Gradient Tracking under the KL Property

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xiaokai, Cao, Tianyu, Scutari, Gesualdo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909425574346752
author Chen, Xiaokai
Cao, Tianyu
Scutari, Gesualdo
author_facet Chen, Xiaokai
Cao, Tianyu
Scutari, Gesualdo
contents We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a convex extended-value function, which enforces constraints or extra structure on the solution (e.g., sparsity, low-rank). We further assume that the objective function satisfies the Kurdyka-Łojasiewicz (KL) property, with given exponent $θ\in [0,1)$. The KL property is satisfied by several (nonconvex) functions of practical interest, e.g., arising from machine learning applications; in the centralized setting, it permits to achieve strong convergence guarantees. Here we establish convergence of the same type for the notorious decentralized gradient-tracking-based algorithm SONATA. Specifically, $\textbf{(i)}$ when $θ\in (0,1/2]$, the sequence generated by SONATA converges to a stationary solution of the problem at R-linear rate;$ \textbf{(ii)} $when $θ\in (1/2,1)$, sublinear rate is certified; and finally $\textbf{(iii)}$ when $θ=0$, the iterates will either converge in a finite number of steps or converges at R-linear rate. This matches the convergence behavior of centralized proximal-gradient algorithms except when $θ=0$. Numerical results validate our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09556
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Convergence of Decentralized Gradient Tracking under the KL Property
Chen, Xiaokai
Cao, Tianyu
Scutari, Gesualdo
Optimization and Control
Machine Learning
Systems and Control
We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a convex extended-value function, which enforces constraints or extra structure on the solution (e.g., sparsity, low-rank). We further assume that the objective function satisfies the Kurdyka-Łojasiewicz (KL) property, with given exponent $θ\in [0,1)$. The KL property is satisfied by several (nonconvex) functions of practical interest, e.g., arising from machine learning applications; in the centralized setting, it permits to achieve strong convergence guarantees. Here we establish convergence of the same type for the notorious decentralized gradient-tracking-based algorithm SONATA. Specifically, $\textbf{(i)}$ when $θ\in (0,1/2]$, the sequence generated by SONATA converges to a stationary solution of the problem at R-linear rate;$ \textbf{(ii)} $when $θ\in (1/2,1)$, sublinear rate is certified; and finally $\textbf{(iii)}$ when $θ=0$, the iterates will either converge in a finite number of steps or converges at R-linear rate. This matches the convergence behavior of centralized proximal-gradient algorithms except when $θ=0$. Numerical results validate our theoretical findings.
title Enhancing Convergence of Decentralized Gradient Tracking under the KL Property
topic Optimization and Control
Machine Learning
Systems and Control
url https://arxiv.org/abs/2412.09556