Complexity analysis of interior point algorithms for non-Lipschitz and nonconvex minimization

• 成果类型: Article
• 署名作者: Bian, Wei; Chen, Xiaojun; Ye, Yinyu
• 署名单位: Harbin Institute of Technology; Hong Kong Polytechnic University; Stanford University
• 刊物名称: MATHEMATICAL PROGRAMMING
• ISSN/ISSBN: 0025-5610
• DOI: 10.1007/s10107-014-0753-5
• 发表日期: 2015
• 页码: 301-327
• 关键词: worst-case complexity; cubic regularization; Newton method; nonsmooth; optimality; selection

摘要

We propose a first order interior point algorithm for a class of non-Lipschitz and nonconvex minimization problems with box constraints, which arise from applications in variable selection and regularized optimization. The objective functions of these problems are continuously differentiable typically at interior points of the feasible set. Our first order algorithm is easy to implement and the objective function value is reduced monotonically along the iteration points. We show that the worst-case iteration complexity for finding an scaled first order stationary point is . Furthermore, we develop a second order interior point algorithm using the Hessian matrix, and solve a quadratic program with a ball constraint at each iteration. Although the second order interior point algorithm costs more computational time than that of the first order algorithm in each iteration, its worst-case iteration complexity for finding an scaled second order stationary point is reduced to . Note that an scaled second order stationary point must also be an scaled first order stationary point.