A Homogeneous Second-Order Descent Method for Nonconvex Optimization

MaRDI QIDQ6417349zbMATH OpenFDO

Authors Chuwen Zhang, Dongdong Ge, Chang He, Bo Jiang, Yuntian Jiang, Chenyu Xue, Yinyu Ye

Publication date 15 November 2022

Has companion code repository https://github.com/COPT-Public/DRSOM.jl

Abstract: In this paper, we introduce a Homogeneous Second-Order Descent Method (HSODM) using the homogenized quadratic approximation to the original function. The merit of homogenization is that only the leftmost eigenvector of a gradient-Hessian integrated matrix is computed at each iteration. Therefore, the algorithm is a single-loop method that does not need to switch to other sophisticated algorithms, and is easy to be implemented. We show that HSODM has a global convergence rate of $O(epsilo{n}^{-3/2})$ to find an $epsilon$-approximate second-order stationary point, and has a local quadratic convergence rate under the standard assumptions. The numerical results demonstrate the advantage of the proposed method over other second-order methods.

This page was built for publication: A Homogeneous Second-Order Descent Method for Nonconvex Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6417349)