Calculus of the Exponent of Kurdyka–Łojasiewicz Inequality and Its Applications to Linear Convergence of First-Order Methods

Guoyin Li University of New South Wales Ting Kei Pong The Hong Kong Polytechnic University

Optimization and Control mathscidoc:1903.27004

Foundations of Computational Mathematics, 18, (5), 1199–1232, 2018
In this paper, we study the Kurdyka–Łojasiewicz (KL) exponent, an important quantity for analyzing the convergence rate of first-order methods. Specifically, we develop various calculus rules to deduce the KL exponent of new (possibly nonconvex and nonsmooth) functions formed from functions with known KL exponents. In addition, we show that the well-studied Luo–Tseng error bound together with a mild assumption on the separation of stationary values implies that the KL exponent is 1/2 . The Luo–Tseng error bound is known to hold for a large class of concrete structured optimization problems, and thus we deduce the KL exponent of a large class of functions whose exponents were previously unknown. Building upon this and the calculus rules, we are then able to show that for many convex or nonconvex optimization models for applications such as sparse recovery, their objective function’s KL exponent is 1/2 . This includes the least squares problem with smoothly clipped absolute deviation regularization or minimax concave penalty regularization and the logistic regression problem with l_1 regularization. Since many existing local convergence rate analysis for first-order methods in the nonconvex scenario relies on the KL exponent,our results enable us to obtain explicit convergence rate for various first-order methods when they are applied to a large variety of practical optimization models. Finally, we further illustrate how our results can be applied to establishing local linear convergence of the proximal gradient algorithm and the inertial proximal algorithm with constant step sizes for some specific models that arise in sparse recovery.
First-order methods, Kurdyka–Łojasiewicz inequality, Error bound, Sparse optimization
[ Download ] [ 2019-03-19 23:44:20 uploaded by gyli ] [ 804 downloads ] [ 0 comments ]
@inproceedings{guoyin2018calculus,
  title={Calculus of the Exponent of Kurdyka–Łojasiewicz Inequality and Its Applications to Linear Convergence of First-Order Methods},
  author={Guoyin Li, and Ting Kei Pong},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20190319234421158501214},
  booktitle={Foundations of Computational Mathematics},
  volume={18},
  number={5},
  pages={1199–1232},
  year={2018},
}
Guoyin Li, and Ting Kei Pong. Calculus of the Exponent of Kurdyka–Łojasiewicz Inequality and Its Applications to Linear Convergence of First-Order Methods. 2018. Vol. 18. In Foundations of Computational Mathematics. pp.1199–1232. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20190319234421158501214.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved