Distributed Stochastic Nonconvex Optimization and Learning based on Successive Convex Approximation

Abstract

We study distributed stochastic nonconvex optimization in multi-agent networks. We introduce a novel algorithmic framework for the distributed minimization of the sum of the expected value of a smooth (possibly nonconvex) function (the agents' sum-utility) plus a convex (possibly nonsmooth) regularizer. The proposed method hinges on successive convex approximation (SCA) techniques, leveraging dynamic consensus as a mechanism to track the average gradient among the agents, and recursive averaging to recover the expected gradient of the sum-utility function. Almost sure convergence to (stationary) solutions of the nonconvex problem is established. Finally, the method is applied to distributed stochastic training of neural networks. Numerical results confirm the theoretical claims, and illustrate the advantages of the proposed method with respect to other methods available in the literature.

arXiv commentProceedings of 2019 Asilomar Conference on Signals, Systems, and Computers

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Constrained Consensus
• Diffusion Adaptation Strategies for Distributed Optimization and Learning over Networks
• Decomposition by Partial Linearization: Parallel Optimization of Multi-Agent Systems
• Sparse Distributed Learning Based on Diffusion Adaptation
• Parallel Selective Algorithms for Big Data Optimization
• A Parallel Stochastic Approximation Method for Nonconvex Multi-Agent Optimization Problems
• A Framework for Parallel and Distributed Training of Neural Networks