Polyak's Heavy Ball Method Achieves Accelerated Local Rate of Convergence under Polyak-Lojasiewicz Inequality

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kassing, Sebastian, Weissmann, Simon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915765023670272
author Kassing, Sebastian
Weissmann, Simon
author_facet Kassing, Sebastian
Weissmann, Simon
contents In this work, we analyze the convergence of Polyak's heavy ball method in both continuous and discrete time for non-convex $C^4$-objective functions satisfying the Polyak-Lojasiewicz inequality. Under this weak assumption, we recover the asymptotic convergence rates originally derived by Polyak in [Polyak, U.S.S.R. Comput. Math. and Math. Phys., 1964] for strongly convex objectives. Our results demonstrate that the heavy ball method exhibits asymptotic local acceleration on this class of functions. In particular, in the discrete time setting, we prove local convergence of the iterates to a minimum once the method enters a sufficiently small neighborhood of the set of minima, for a broad range of hyperparameters, including aggressive choices for the momentum parameter and the step-size for which global convergence is known to fail. Instead of the usually employed Lyapunov-type arguments, our approach leverages a new differential geometric perspective of the Polyak-Lojasiewicz inequality proposed in [Rebjock and Boumal, Math. Program., 2025].
format Preprint
id arxiv_https___arxiv_org_abs_2410_16849
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Polyak's Heavy Ball Method Achieves Accelerated Local Rate of Convergence under Polyak-Lojasiewicz Inequality
Kassing, Sebastian
Weissmann, Simon
Optimization and Control
Machine Learning
Primary 90C26, Secondary 90C30, 37C10, 34D45
In this work, we analyze the convergence of Polyak's heavy ball method in both continuous and discrete time for non-convex $C^4$-objective functions satisfying the Polyak-Lojasiewicz inequality. Under this weak assumption, we recover the asymptotic convergence rates originally derived by Polyak in [Polyak, U.S.S.R. Comput. Math. and Math. Phys., 1964] for strongly convex objectives. Our results demonstrate that the heavy ball method exhibits asymptotic local acceleration on this class of functions. In particular, in the discrete time setting, we prove local convergence of the iterates to a minimum once the method enters a sufficiently small neighborhood of the set of minima, for a broad range of hyperparameters, including aggressive choices for the momentum parameter and the step-size for which global convergence is known to fail. Instead of the usually employed Lyapunov-type arguments, our approach leverages a new differential geometric perspective of the Polyak-Lojasiewicz inequality proposed in [Rebjock and Boumal, Math. Program., 2025].
title Polyak's Heavy Ball Method Achieves Accelerated Local Rate of Convergence under Polyak-Lojasiewicz Inequality
topic Optimization and Control
Machine Learning
Primary 90C26, Secondary 90C30, 37C10, 34D45
url https://arxiv.org/abs/2410.16849