A note on the convergence of nonconvex line search

2016/03/19 by Sun, Tao, Chenga, Lizhi, Jiang, Hao
#FOS: Mathematics #Numerical Analysis (math.NA)

paper · doi:10.48550/arxiv.1603.06912

Abstract

In this note, we consider the line search for a class of abstract nonconvex algorithm which have been deeply studied in the Kurdyka-Lojasiewicz theory. We provide a weak convergence result of the line search in general. When the objective function satisfies the Kurdyka-Lojasiewicz property and some certain assumption, a global convergence result can be derived. An application is presented for the L0-regularized least square minimization in the end of the paper.

Related

• Complexity analysis of second-order line-search algorithms for smooth\n nonconvex optimization
• On the Global Convergence of Majorization Minimization Algorithms for Nonconvex Optimization Problems
• Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods
• A Non-Monotone Line-Search Method for Minimizing Functions with Spurious Local Minima
• Global Convergence Rate Analysis of a Generic Line Search Algorithm with\n Noise