Logarithmically Quantized Distributed Optimization over Dynamic Multi-Agent Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Doostmohammadian, Mohammadreza, Pequito, Sérgio
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909366712532992
author Doostmohammadian, Mohammadreza
Pequito, Sérgio
author_facet Doostmohammadian, Mohammadreza
Pequito, Sérgio
contents Distributed optimization finds many applications in machine learning, signal processing, and control systems. In these real-world applications, the constraints of communication networks, particularly limited bandwidth, necessitate implementing quantization techniques. In this paper, we propose distributed optimization dynamics over multi-agent networks subject to logarithmically quantized data transmission. Under this condition, data exchange benefits from representing smaller values with more bits and larger values with fewer bits. As compared to uniform quantization, this allows for higher precision in representing near-optimal values and more accuracy of the distributed optimization algorithm. The proposed optimization dynamics comprise a primary state variable converging to the optimizer and an auxiliary variable tracking the objective function's gradient. Our setting accommodates dynamic network topologies, resulting in a hybrid system requiring convergence analysis using matrix perturbation theory and eigenspectrum analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20345
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Logarithmically Quantized Distributed Optimization over Dynamic Multi-Agent Networks
Doostmohammadian, Mohammadreza
Pequito, Sérgio
Systems and Control
Machine Learning
Multiagent Systems
Optimization and Control
Distributed optimization finds many applications in machine learning, signal processing, and control systems. In these real-world applications, the constraints of communication networks, particularly limited bandwidth, necessitate implementing quantization techniques. In this paper, we propose distributed optimization dynamics over multi-agent networks subject to logarithmically quantized data transmission. Under this condition, data exchange benefits from representing smaller values with more bits and larger values with fewer bits. As compared to uniform quantization, this allows for higher precision in representing near-optimal values and more accuracy of the distributed optimization algorithm. The proposed optimization dynamics comprise a primary state variable converging to the optimizer and an auxiliary variable tracking the objective function's gradient. Our setting accommodates dynamic network topologies, resulting in a hybrid system requiring convergence analysis using matrix perturbation theory and eigenspectrum analysis.
title Logarithmically Quantized Distributed Optimization over Dynamic Multi-Agent Networks
topic Systems and Control
Machine Learning
Multiagent Systems
Optimization and Control
url https://arxiv.org/abs/2410.20345