EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimization and Learning in Open Multiagent Systems

Diego Deplano, Nicola Bastianello, Mauro Franceschelli, Karl H. Johansson

IEEE Transactions on Automatic Control · 2026-06 · 71 (6) · 3864-3879

DOI: 10.1109/tac.2026.3653296 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Automatic Control, 2026-06. Verfasst von Diego Deplano und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: e.INS-Ecosystem of Innovation for Next Generation Sardinia, Italian Ministry for Research and Education, National Recovery and Resilience Plan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern artificial intelligence relies on networks of agents that collect data, process information, and exchange it with neighbors to collaboratively solve optimization and learning problems. This article introduces a novel distributed algorithm to address a broad class of these problems in open networks, where the number of participating agents may vary due to several factors, such as autonomous decisions, heterogeneous resource availability, or denial of service (DoS) attacks. Extending the current literature, the convergence analysis of the proposed algorithm is based on the newly developed Theory of Open Operators, which characterizes an operator as open when the set of components to be updated changes over time, yielding time-varying operators acting on sequences of points of different dimensions and compositions. The mathematical tools and convergence results developed here provide a general framework for evaluating distributed algorithms in open networks, enabling characterization of their performance in terms of the punctual distance to the optimal solution, in contrast with regret-based metrics that assess cumulative performance over a finite-time horizon. As illustrative examples, the proposed algorithm is used to solve dynamic consensus and tracking problems on different metrics, such as average, median, and min/max, as well as classification problems with logistic loss functions.

Förderung

  • e.INS-Ecosystem of Innovation for Next Generation Sardinia
  • Italian Ministry for Research and Education
  • National Recovery and Resilience Plan
  • From research to business
  • Creation and strengthening of Ecosystems of innovation
  • Territorial R& D Leaders
  • European Union’s Horizon Research and Innovation Actions programme
  • Swedish Research Council Distinguished Professor

Zitieren

APA

Deplano, D., Bastianello, N., Franceschelli, M., & Johansson, K. H. (2026). Optimization and Learning in Open Multiagent Systems. IEEE Transactions on Automatic Control, 71(6), 3864-3879. https://doi.org/10.1109/tac.2026.3653296

Vancouver

Deplano D, Bastianello N, Franceschelli M, Johansson KH. Optimization and Learning in Open Multiagent Systems. IEEE Transactions on Automatic Control. 2026;71(6):3864-3879. doi:10.1109/tac.2026.3653296

BibTeX
@article{Deplano2026,
  author = {Deplano, Diego and Bastianello, Nicola and Franceschelli, Mauro and Johansson, Karl H.},
  title = {Optimization and Learning in Open Multiagent Systems},
  journal = {IEEE Transactions on Automatic Control},
  year = {2026},
  volume = {71},
  number = {6},
  pages = {3864--3879},
  doi = {10.1109/tac.2026.3653296}
}
Kostenlos starten →