# Asynchronous Message-Passing and Zeroth-Order Optimization Based Distributed Learning with a Use-Case in Resource Allocation in Communication Networks

arXiv: https://arxiv.org/abs/2311.04604 · HTML: https://mlsanity.com/paper/2311.04604/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 50 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Builds on (most cited first, 27 of 27)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning](https://mlsanity.com/paper/1702.07464/) (2017)
- [Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning](https://mlsanity.com/paper/1807.06629/) (2018)
- [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning](https://mlsanity.com/paper/1812.00535/) (2018)
- [Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization](https://mlsanity.com/paper/1308.6594/) (2013)
- [Game-Theoretic Multiagent Reinforcement Learning](https://mlsanity.com/paper/2011.00583/) (2020)
- [Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks](https://mlsanity.com/paper/1909.01865/) (2019)
- [Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis](https://mlsanity.com/paper/2007.07632/) (2020)
- [Multi-Agent Deep Reinforcement Learning for Dynamic Power Allocation in Wireless Networks](https://mlsanity.com/paper/1808.00490/) (2018)
- [How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective](https://mlsanity.com/paper/2203.14195/) (2022)
- [Towards Optimal Power Control via Ensembling Deep Neural Networks](https://mlsanity.com/paper/1807.10025/) (2018)
- [Multitask learning over graphs: An Approach for Distributed, Streaming Machine Learning](https://mlsanity.com/paper/2001.02112/) (2020)
- [Learning Decentralized Wireless Resource Allocations with Graph Neural Networks](https://mlsanity.com/paper/2107.01489/) (2021)
- [Distributed Learning in Non-Convex Environments -- Part I: Agreement at a Linear Rate](https://mlsanity.com/paper/1907.01848/) (2019)
- [Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties](https://mlsanity.com/paper/1403.3862/) (2014)
- [ARock: an Algorithmic Framework for Asynchronous Parallel Coordinate Updates](https://mlsanity.com/paper/1506.02396/) (2015)
- [Learning Resilient Radio Resource Management Policies with Graph Neural Networks](https://mlsanity.com/paper/2203.11012/) (2022)
- [State-Augmented Learnable Algorithms for Resource Management in Wireless Networks](https://mlsanity.com/paper/2207.02242/) (2022)
- [Zeroth Order Nonconvex Multi-Agent Optimization over Networks](https://mlsanity.com/paper/1710.09997/) (2017)
- [A New Randomized Block-Coordinate Primal-Dual Proximal Algorithm for Distributed Optimization](https://mlsanity.com/paper/1706.02882/) (2017)
- [Learning over Multitask Graphs -- Part I: Stability Analysis](https://mlsanity.com/paper/1805.08535/) (2018)
- [Distributed Proximal Gradient Algorithm for Partially Asynchronous Computer Clusters](https://mlsanity.com/paper/1704.03540/) (2017)
- [Deep Learning for Radio Resource Allocation with Diverse Quality-of-Service Requirements in 5G](https://mlsanity.com/paper/2004.00507/) (2020)
- [Model-Free Learning of Optimal Ergodic Policies in Wireless Systems](https://mlsanity.com/paper/1911.03988/) (2019)
- [Learning in Wireless Control Systems over Non-Stationary Channels](https://mlsanity.com/paper/1803.01078/) (2018)

## Abstract (arXiv)

Distributed learning and adaptation have received significant interest and found wide-ranging applications in machine learning and signal processing. While various approaches, such as shared-memory optimization, multi-task learning, and consensus-based learning (e.g., federated learning and learning over graphs), focus on optimizing either local costs or a global cost, there remains a need for further exploration of their interconnections. This paper specifically focuses on a scenario where agents collaborate towards a common task (i.e., optimizing a global cost equal to aggregated local costs) while effectively having distinct individual tasks (i.e., optimizing individual local parameters in a local cost). Each agent's actions can potentially impact other agents' performance through interactions. Notably, each agent has access to only its local zeroth-order oracle (i.e., cost function value) and shares scalar values, rather than gradient vectors, with other agents, leading to communication bandwidth efficiency and agent privacy. Agents employ zeroth-order optimization to update their parameters, and the asynchronous message-passing between them is subject to bounded but possibly random communication delays. This paper presents theoretical convergence analyses and establishes a convergence rate for nonconvex problems. Furthermore, it addresses the relevant use-case of deep learning-based resource allocation in communication networks and conducts numerical experiments in which agents, acting as transmitters, collaboratively train their individual policies to maximize a global reward, e.g., a sum of data rates.