The Proximal Alternating Direction Method of Multipliers in the Nonconvex Setting: Convergence Analysis and Rates

• 成果类型: Article
• 署名作者: Bot, Radu Ioan; Dang-Khoa Nguyen
• 署名单位: University of Vienna; Babes Bolyai University from Cluj
• 刊物名称: MATHEMATICS OF OPERATIONS RESEARCH
• ISSN/ISSBN: 0364-765X
• DOI: 10.1287/moor.2019.1008
• 发表日期: 2020
• 页码: 682-712
• 关键词: splitting algorithm; minimization; nonsmooth; points; SUM

摘要

We propose two numerical algorithms in the fully nonconvex setting for the minimization of the sum of a smooth function and the composition of a nonsmooth function with a linear operator. The iterative schemes are formulated in the spirit of the proximal alternating direction method of multipliers and its linearized variant, respectively. The proximal terms are introduced via variable metrics, a fact that allows us to derive new proximal splitting algorithms for nonconvex structured optimization problems, as particular instances of the general schemes. Under mild conditions on the sequence of variable metrics and by assuming that a regularization of the associated augmented Lagrangian has the Kurdyka-Lojasiewicz property, we prove that the iterates converge to a Karush-Kuhn-Tucker point of the objective function. By assuming that the augmented Lagrangian has the Lojasiewicz property, we also derive convergence rates for both the augmented Lagrangian and the iterates.