Distributed Associative Memory via Online Convex Optimization

• URL: http://arxiv.org/abs/2509.22321v1
• Date: Fri, 26 Sep 2025 13:20:15 GMT
• Title: Distributed Associative Memory via Online Convex Optimization
• Authors: Bowen Wang, Matteo Zecchin, Osvaldo Simeone,
• Abstract summary: 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.<n>This work addresses a distributed setting where agents maintain a local AM to recall their own associations as well as selective information from others.
• Score: 42.94410959330529
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations [61.6579785305668]
  AMemGym is an interactive environment enabling on-policy evaluation and optimization for memory-driven personalization.<n>Our framework provides a scalable, diagnostically rich environment for advancing memory capabilities in conversational agents.
  arXiv  Detail & Related papers  (2026-03-02T15:15:11Z)
• RecNet: Self-Evolving Preference Propagation for Agentic Recommender Systems [109.9061591263748]
  RecNet is a self-evolving preference propagation framework for recommender systems.<n>It proactively propagates real-time preference updates across related users and items.<n>In the backward phase, the feedback-driven propagation optimization mechanism simulates a multi-agent reinforcement learning framework.
  arXiv  Detail & Related papers  (2026-01-29T12:14:31Z)
• MemRec: Collaborative Memory-Augmented Agentic Recommender System [57.548438733740504]
  We propose MemRec, a framework that architecturally decouples reasoning from memory management.<n>MemRec introduces a dedicated LM_Mem to manage a dynamic collaborative memory graph.<n>It achieves state-of-the-art performance on four benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T18:51:16Z)
• Distributed Dynamic Associative Memory via Online Convex Optimization [42.94410959330529]
  An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architectures such as Transformers.<n>We introduce the concept of distributed dynamic associative memory (DDAM), which extends classical AM to settings with multiple agents and time-varying data streams.<n>In DDAM, each agent maintains a local AM that must not only store its own associations but also selectively memorize information from other agents based on a specified interest matrix.<n>We propose a novel tree-based distributed gradient online descent algorithm, termed DDAM-TOGD, which enables each agent to
  arXiv  Detail & Related papers  (2025-11-28T16:56:18Z)
• Nonparametric Bellman Mappings for Value Iteration in Distributed Reinforcement Learning [3.5051814539447474]
  This paper introduces novel Bellman mappings (B-Maps) for value iteration (VI) in distributed reinforcement learning (DRL)<n>B-Maps operate on Q-functions represented in a kernel Hilbert space, enabling a nonparametric formulation.<n> Numerical experiments on two well-known control problems demonstrate the superior performance of the proposed nonparametric B-Maps.
  arXiv  Detail & Related papers  (2025-03-20T14:39:21Z)
• Joint Optimal Transport and Embedding for Network Alignment [66.49765320358361]
  We propose a joint optimal transport and embedding framework for network alignment named JOENA.<n>With a unified objective, the mutual benefits of both methods can be achieved by an alternating optimization schema with guaranteed convergence.<n>Experiments on real-world networks validate the effectiveness and scalability of JOENA, achieving up to 16% improvement in MRR and 20x speedup.
  arXiv  Detail & Related papers  (2025-02-26T17:28:08Z)
• Online Reinforcement Learning with Passive Memory [17.293733942245154]
  We show that using passive memory improves performance and provides theoretical guarantees for regret that turns out to be near-minimax optimal. Results show that the quality of passive memory determines sub-optimality of the incurred regret.
  arXiv  Detail & Related papers  (2024-10-18T17:55:15Z)
• Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization [75.1240295759264]
  We propose an effective framework for Bridging and Modeling Correlations in pairwise data, named BMC.<n>We increase the consistency and informativeness of the pairwise preference signals through targeted modifications.<n>We identify that DPO alone is insufficient to model these correlations and capture nuanced variations.
  arXiv  Detail & Related papers  (2024-08-14T11:29:47Z)
• UAV-assisted Semantic Communication with Hybrid Action Reinforcement Learning [19.48293218551122]
  We propose a hybrid action reinforcement learning framework to make decisions on semantic model scale, channel allocation, transmission power, and UAV trajectory. Simulation results indicate that the proposed hybrid action reinforcement learning framework can effectively improve the efficiency of uplink semantic data collection.
  arXiv  Detail & Related papers  (2023-08-18T06:30:18Z)
• Compressed Regression over Adaptive Networks [58.79251288443156]
  We derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints, a regression problem. We devise an optimized allocation strategy where the parameters necessary for the optimization can be learned online by the agents.
  arXiv  Detail & Related papers  (2023-04-07T13:41:08Z)
• Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity [44.2308932471393]
  We show that exchanging model estimates leads to linear convergence speedups in the number of agents. In a low-heterogeneity regime, exchanging model estimates leads to linear convergence speedups in the number of agents.
  arXiv  Detail & Related papers  (2023-02-04T17:53:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.