Multi-Agent Optimization and Learning: A Non-Expansive Operators Perspective

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bastianello, Nicola, Schenato, Luca, Carli, Ruggero
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911135151685632
author Bastianello, Nicola
Schenato, Luca
Carli, Ruggero
author_facet Bastianello, Nicola
Schenato, Luca
Carli, Ruggero
contents Multi-agent systems are increasingly widespread in a range of application domains, with optimization and learning underpinning many of the tasks that arise in this context. Different approaches have been proposed to enable the cooperative solution of these optimization and learning problems, including first- and second-order methods, and dual (or Lagrangian) methods, all of which rely on consensus and message-passing. In this article we discuss these algorithms through the lens of non-expansive operator theory, providing a unifying perspective. We highlight the insights that this viewpoint delivers, and discuss how it can spark future original research.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11999
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Agent Optimization and Learning: A Non-Expansive Operators Perspective
Bastianello, Nicola
Schenato, Luca
Carli, Ruggero
Optimization and Control
Systems and Control
Multi-agent systems are increasingly widespread in a range of application domains, with optimization and learning underpinning many of the tasks that arise in this context. Different approaches have been proposed to enable the cooperative solution of these optimization and learning problems, including first- and second-order methods, and dual (or Lagrangian) methods, all of which rely on consensus and message-passing. In this article we discuss these algorithms through the lens of non-expansive operator theory, providing a unifying perspective. We highlight the insights that this viewpoint delivers, and discuss how it can spark future original research.
title Multi-Agent Optimization and Learning: A Non-Expansive Operators Perspective
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2405.11999