Research
Distributed Associative Memory via Online Convex Optimization
arXiv:2509.22321v2 Announce Type: replace Abstract: An associative memory (AM) enables cue-response recall, and associative memorization has recently been noted to underlie the operation of modern neu
arXiv:2509.22321v2 Announce Type: replace 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.
Related
- Distributed Online Convex Optimization with Compressed Communication: Optimal Regret and Applications
- Tighter Performance Theory of FedExProx
- DADA: Dual Averaging with Distance Adaptation
- Learning to accelerate distributed ADMM using graph neural networks
- Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
Source: arXiv cs.LG | 2026-04-24