Work

Distributed Associative Memory Via Online Convex Optimization

Year: 2026

Type: conference-paper

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.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp55912.2026.11464435

Authors: Bowen Wang, Matteo Zecchin, Osvaldo Simeone

Institutions: King's College London, EURECOM, Northeastern University London

Language: English

Topic: Distributed Control Multi-Agent Systems

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: King's College London, European Commission, HORIZON EUROPE Framework Programme, Engineering and Physical Sciences Research Council

Awards: FreeML: Engineering Networked Machine Learning via Meta-Free Energy Minimisation, ECCS-EPSRC: NeuroComm: Brain-Inspired Wireless Communications -- From Theoretical Foundations to Implementation for 6G and Beyond