Distributed Associative Memory via Online Convex Optimization
Machine Learning
2026-04-24 v2 Signal Processing
Abstract
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.
Cite
@article{arxiv.2509.22321,
title = {Distributed Associative Memory via Online Convex Optimization},
author = {Bowen Wang and Matteo Zecchin and Osvaldo Simeone},
journal= {arXiv preprint arXiv:2509.22321},
year = {2026}
}