HBNET-GIANT: A communication-efficient accelerated Newton-type fully distributed optimization algorithm

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Das, Souvik, Schenato, Luca, Dey, Subhrakanti
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912715205771264
author Das, Souvik
Schenato, Luca
Dey, Subhrakanti
author_facet Das, Souvik
Schenato, Luca
Dey, Subhrakanti
contents This article presents a second-order fully distributed optimization algorithm, HBNET-GIANT, driven by heavy-ball momentum, for $L$-smooth and $μ$-strongly convex objective functions. A rigorous convergence analysis is performed, and we demonstrate global linear convergence under certain sufficient conditions. Through extensive numerical experiments, we show that HBNET-GIANT with heavy-ball momentum achieves acceleration, and the corresponding rate of convergence is strictly faster than its non-accelerated version, NETWORK-GIANT. Moreover, we compare HBNET-GIANT with several state-of-the-art algorithms, both momentum-based and without momentum, and report significant performance improvement in convergence to the optimum. We believe that this work lays the groundwork for a broader class of second-order Newton-type algorithms with momentum and motivates further investigation into open problems, including an analytical proof of local acceleration in the fully distributed setting for convex optimization problems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13584
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HBNET-GIANT: A communication-efficient accelerated Newton-type fully distributed optimization algorithm
Das, Souvik
Schenato, Luca
Dey, Subhrakanti
Optimization and Control
Signal Processing
This article presents a second-order fully distributed optimization algorithm, HBNET-GIANT, driven by heavy-ball momentum, for $L$-smooth and $μ$-strongly convex objective functions. A rigorous convergence analysis is performed, and we demonstrate global linear convergence under certain sufficient conditions. Through extensive numerical experiments, we show that HBNET-GIANT with heavy-ball momentum achieves acceleration, and the corresponding rate of convergence is strictly faster than its non-accelerated version, NETWORK-GIANT. Moreover, we compare HBNET-GIANT with several state-of-the-art algorithms, both momentum-based and without momentum, and report significant performance improvement in convergence to the optimum. We believe that this work lays the groundwork for a broader class of second-order Newton-type algorithms with momentum and motivates further investigation into open problems, including an analytical proof of local acceleration in the fully distributed setting for convex optimization problems.
title HBNET-GIANT: A communication-efficient accelerated Newton-type fully distributed optimization algorithm
topic Optimization and Control
Signal Processing
url https://arxiv.org/abs/2511.13584