Online Distributed Learning with Quantized Finite-Time Coordination

TL;DR

This paper introduces a peer-to-peer distributed learning algorithm that uses quantized finite-time coordination and stochastic gradients, enabling efficient, privacy-preserving model training without a central server.

Contribution

The paper proposes a novel decentralized algorithm with quantized finite-time coordination and stochastic gradients for online distributed learning.

Findings

Algorithm achieves finite-time convergence.

Supports stochastic gradients for scalability.

Numerical results validate effectiveness on logistic regression.

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.