Multi-agent online optimization with delays: Asynchronicity, adaptivity, and optimism - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Machine Learning Research Year : 2022

Multi-agent online optimization with delays: Asynchronicity, adaptivity, and optimism

Abstract

In this paper, we provide a general framework for studying multi-agent online learning problems in the presence of delays and asynchronicities. Specifically, we propose and analyze a class of adaptive dual averaging schemes in which agents only need to accumulate gradient feedback received from the whole system, without requiring any between-agent coordination. In the single-agent case, the adaptivity of the proposed method allows us to extend a range of existing results to problems with potentially unbounded delays between playing an action and receiving the corresponding feedback. In the multi-agent case, the situation is significantly more complicated because agents may not have access to a global clock to use as a reference point; to overcome this, we focus on the information that is available for producing each prediction rather than the actual delay associated with each feedback. This allows us to derive adaptive learning strategies with optimal regret bounds, even in a fully decentralized, asynchronous environment. Finally, we also analyze an "optimistic" variant of the proposed algorithm which is capable of exploiting the predictability of problems with a slower variation and leads to improved regret bounds.
Fichier principal
Vignette du fichier
main.pdf (606 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03410422 , version 1 (31-10-2021)

Identifiers

  • HAL Id : hal-03410422 , version 1

Cite

Yu-Guan Hsieh, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos. Multi-agent online optimization with delays: Asynchronicity, adaptivity, and optimism. Journal of Machine Learning Research, 2022, 23 (78), pp.1--49. ⟨hal-03410422⟩
131 View
116 Download

Share

Gmail Facebook X LinkedIn More