Quasi-Newton Updating for Large-Scale Distributed Learning

Autor:	Wu, Shuyuan, Huang, Danyang, Wang, Hansheng
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Distributed Parallel and Cluster Computing Statistics - Methodology
Druh dokumentu:	Working Paper
Popis:	Distributed computing is critically important for modern statistical analysis. Herein, we develop a distributed quasi-Newton (DQN) framework with excellent statistical, computation, and communication efficiency. In the DQN method, no Hessian matrix inversion or communication is needed. This considerably reduces the computation and communication complexity of the proposed method. Notably, related existing methods only analyze numerical convergence and require a diverging number of iterations to converge. However, we investigate the statistical properties of the DQN method and theoretically demonstrate that the resulting estimator is statistically efficient over a small number of iterations under mild conditions. Extensive numerical analyses demonstrate the finite sample performance. Comment: 56 pages, 3 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.04111 Zobrazit plný text záznamu View this record from Arxiv