Distributed Associative Memory via Online Convex Optimization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Bowen, Zecchin, Matteo, Simeone, Osvaldo
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914501253660672
author Wang, Bowen
Zecchin, Matteo
Simeone, Osvaldo
author_facet Wang, Bowen
Zecchin, Matteo
Simeone, Osvaldo
contents An associative memory (AM) enables cue-response recall, and associative memorization has recently been noted to underlie the operation of modern neural architectures such as Transformers. This work addresses a distributed setting where agents maintain a local AM to recall their own associations as well as selective information from others. Specifically, we introduce a distributed online gradient descent method that optimizes local AMs at different agents through communication over routing trees. Our theoretical analysis establishes sublinear regret guarantees, and experiments demonstrate that the proposed protocol consistently outperforms existing online optimization baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22321
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Distributed Associative Memory via Online Convex Optimization
Wang, Bowen
Zecchin, Matteo
Simeone, Osvaldo
Machine Learning
Signal Processing
An associative memory (AM) enables cue-response recall, and associative memorization has recently been noted to underlie the operation of modern neural architectures such as Transformers. This work addresses a distributed setting where agents maintain a local AM to recall their own associations as well as selective information from others. Specifically, we introduce a distributed online gradient descent method that optimizes local AMs at different agents through communication over routing trees. Our theoretical analysis establishes sublinear regret guarantees, and experiments demonstrate that the proposed protocol consistently outperforms existing online optimization baselines.
title Distributed Associative Memory via Online Convex Optimization
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2509.22321