Scalable Decentralized Algorithms for Online Personalized Mean Estimation - 3IA Côte d’Azur – Interdisciplinary Institute for Artificial Intelligence
Communication Dans Un Congrès Année : 2025

Scalable Decentralized Algorithms for Online Personalized Mean Estimation

Résumé

In numerous settings, agents lack sufficient data to learn a model directly. Collaborating with other agents may help, but introduces a bias-variance trade-off when local data distributions differ. A key challenge is for each agent to identify clients with similar distributions while learning the model, a problem that remains largely unresolved. This study focuses on a particular instance of the overarching problem, where each agent collects samples from a real-valued distribution over time to estimate its mean. Existing algorithms face impractical per-agent space and time complexities (linear in the number of agents |A|). To address scalability challenges, we propose a framework where agents self-organize into a graph, allowing each agent to communicate with only a selected number of peers r. We propose two collaborative mean estimation algorithms: one employs a consensus-based approach, while the other uses a message-passing scheme, with complexity O(r) and O(r • log |A|), respectively. We establish conditions for both algorithms to yield asymptotically optimal estimates and we provide a theoretical characterization of their performance.
Fichier principal
Vignette du fichier
AAAI25_Camera_Ready_SUBMISSION.pdf (1.02 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04878986 , version 1 (10-01-2025)

Licence

Identifiants

  • HAL Id : hal-04878986 , version 1

Citer

Franco Galante, Giovanni Neglia, Emilio Leonardi. Scalable Decentralized Algorithms for Online Personalized Mean Estimation. 39th Annual AAAI Conference on Artificial Intelligence - AAAI 2025, Feb 2025, Philadelphia (Pennsylvania), United States. ⟨hal-04878986⟩
0 Consultations
0 Téléchargements

Partager

More