Communication-Efficient Frank-Wolfe Algorithm for Nonconvex Decentralized Distributed Learning

Authors

  • Wenhan Xian University of Pittsburgh
  • Feihu Huang University of Pittsburgh
  • Heng Huang University of Pittsburgh JD Finance America Corporation

Keywords:

Optimization, Distributed Machine Learning & Federated Learning

Abstract

Recently decentralized optimization attracts much attention in machine learning because it is more communication-efficient than the centralized fashion. Quantization is a promising method to reduce the communication cost via cutting down the budget of each single communication using the gradient compression. To further improve the communication efficiency, more recently, some quantized decentralized algorithms have been studied. However, the quantized decentralized algorithm for nonconvex constrained machine learning problems is still limited. Frank-Wolfe (a.k.a., conditional gradient or projection-free) method is very efficient to solve many constrained optimization tasks, such as low-rank or sparsity-constrained models training. In this paper, to fill the gap of decentralized quantized constrained optimization, we propose a novel communication-efficient Decentralized Quantized Stochastic Frank-Wolfe (DQSFW) algorithm for non-convex constrained learning models. We first design a new counterexample to show that the vanilla decentralized quantized stochastic Frank-Wolfe algorithm usually diverges. Thus, we propose DQSFW algorithm with the gradient tracking technique to guarantee the method will converge to the stationary point of non-convex optimization safely. In our theoretical analysis, we prove that to achieve the stationary point our DQSFW algorithm achieves the same gradient complexity as the standard stochastic Frank-Wolfe and centralized Frank-Wolfe algorithms, but has much less communication cost. Experiments on matrix completion and model compression applications demonstrate the efficiency of our new algorithm.

Downloads

Published

2021-05-18

How to Cite

Xian, W., Huang, F., & Huang, H. (2021). Communication-Efficient Frank-Wolfe Algorithm for Nonconvex Decentralized Distributed Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(12), 10405-10413. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17246

Issue

Section

AAAI Technical Track on Machine Learning V