CoNeT-GIANT: A compressed Newton-type fully distributed optimization algorithm

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Das, Souvik, Dey, Subhrakanti
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915573342928896
author Das, Souvik
Dey, Subhrakanti
author_facet Das, Souvik
Dey, Subhrakanti
contents Compression techniques are essential in distributed optimization and learning algorithms with high-dimensional model parameters, particularly in scenarios with tight communication constraints such as limited bandwidth. This article presents a communication-efficient second-order distributed optimization algorithm, termed as CoNet-GIANT, equipped with a compression module, designed to minimize the average of local strongly convex functions. CoNet-GIANT incorporates two consensus-based averaging steps at each node: gradient tracking and approximate Newton-type iterations, inspired by the recently proposed Network-GIANT. Under certain sufficient conditions on the step size, CoNet-GIANT achieves significantly faster linear convergence, comparable to that of its first-order counterparts, both in the compressed and uncompressed settings. CoNet-GIANT is efficient in terms of data usage, communication cost, and run-time, making it a suitable choice for distributed optimization over a wide range of wireless networks. Extensive experiments on synthetic data and the widely used CovType dataset demonstrate its superior performance.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08806
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoNeT-GIANT: A compressed Newton-type fully distributed optimization algorithm
Das, Souvik
Dey, Subhrakanti
Optimization and Control
Compression techniques are essential in distributed optimization and learning algorithms with high-dimensional model parameters, particularly in scenarios with tight communication constraints such as limited bandwidth. This article presents a communication-efficient second-order distributed optimization algorithm, termed as CoNet-GIANT, equipped with a compression module, designed to minimize the average of local strongly convex functions. CoNet-GIANT incorporates two consensus-based averaging steps at each node: gradient tracking and approximate Newton-type iterations, inspired by the recently proposed Network-GIANT. Under certain sufficient conditions on the step size, CoNet-GIANT achieves significantly faster linear convergence, comparable to that of its first-order counterparts, both in the compressed and uncompressed settings. CoNet-GIANT is efficient in terms of data usage, communication cost, and run-time, making it a suitable choice for distributed optimization over a wide range of wireless networks. Extensive experiments on synthetic data and the widely used CovType dataset demonstrate its superior performance.
title CoNeT-GIANT: A compressed Newton-type fully distributed optimization algorithm
topic Optimization and Control
url https://arxiv.org/abs/2510.08806