English

Distributed Adaptive Newton Methods with Global Superlinear Convergence

Optimization and Control 2022-01-17 v3 Distributed, Parallel, and Cluster Computing Multiagent Systems Systems and Control Signal Processing Systems and Control

Abstract

This paper considers the distributed optimization problem where each node of a peer-to-peer network minimizes a finite sum of objective functions by communicating with its neighboring nodes. In sharp contrast to the existing literature where the fastest distributed algorithms converge either with a global linear or a local superlinear rate, we propose a distributed adaptive Newton (DAN) algorithm with a global quadratic convergence rate. Our key idea lies in the design of a finite-time set-consensus method with Polyak's adaptive stepsize. Moreover, we introduce a low-rank matrix approximation (LA) technique to compress the innovation of Hessian matrix so that each node only needs to transmit message of dimension O(p)\mathcal{O}(p) (where pp is the dimension of decision vectors) per iteration, which is essentially the same as that of first-order methods. Nevertheless, the resulting DAN-LA converges to an optimal solution with a global superlinear rate. Numerical experiments on logistic regression problems are conducted to validate their advantages over existing methods.

Keywords

Cite

@article{arxiv.2002.07378,
  title  = {Distributed Adaptive Newton Methods with Global Superlinear Convergence},
  author = {Jiaqi Zhang and Keyou You and Tamer Başar},
  journal= {arXiv preprint arXiv:2002.07378},
  year   = {2022}
}

Comments

Accepted to Automatica as regular paper. 13 pages

R2 v1 2026-06-23T13:44:53.805Z