Online Distributed Learning with Quantized Finite-Time Coordination

Abstract

In this paper we consider online distributed learning problems. Online distributed learning refers to the process of training learning models on distributed data sources. In our setting a set of agents need to cooperatively train a learning model from streaming data. Differently from federated learning, the proposed approach does not rely on a central server but only on peer-to-peer communications among the agents. This approach is often used in scenarios where data cannot be moved to a centralized location due to privacy, security, or cost reasons. In order to overcome the absence of a central server, we propose a distributed algorithm that relies on a quantized, finite-time coordination protocol to aggregate the locally trained models. Furthermore, our algorithm allows for the use of stochastic gradients during local training. Stochastic gradients are computed using a randomly sampled subset of the local training data, which makes the proposed algorithm more efficient and scalable than traditional gradient descent. In our paper, we analyze the performance of the proposed algorithm in terms of the mean distance from the online solution. Finally, we present numerical results for a logistic regression task.

arXiv commentTo be presented at IEEE CDC'23

References in corpus (9)

• Federated Learning: Challenges, Methods, and Future Directions
• ADD-OPT: Accelerated Distributed Directed Optimization
• Federated Learning: A Signal Processing Perspective
• Online Learning with Inexact Proximal Online Gradient Descent Algorithms
• Distributed Optimization for Smart Cyber-Physical Networks
• Optimization and Learning with Information Streams: Time-varying Algorithms and Applications
• A Unified and Refined Convergence Analysis for Non-Convex Decentralized Learning
• Can Primal Methods Outperform Primal-dual Methods in Decentralized Dynamic Optimization?
• Distributed and Inexact Proximal Gradient Method for Online Convex Optimization

Cited by in corpus (1)

• Asynchronous Distributed Learning with Quantized Finite-Time Coordination