Structured nonconvex and nonsmooth optimization: algorithms and iteration complexity analysis

Bo Jiang (), Tianyi Lin, Shiqian Ma and Shuzhong Zhang
Additional contact information
Bo Jiang: Shanghai University of Finance and Economics
Tianyi Lin: UC Berkeley
Shiqian Ma: UC Davis
Shuzhong Zhang: University of Minnesota

Computational Optimization and Applications, 2019, vol. 72, issue 1, No 4, 115-157

Abstract: Abstract Nonconvex and nonsmooth optimization problems are frequently encountered in much of statistics, business, science and engineering, but they are not yet widely recognized as a technology in the sense of scalability. A reason for this relatively low degree of popularity is the lack of a well developed system of theory and algorithms to support the applications, as is the case for its convex counterpart. This paper aims to take one step in the direction of disciplined nonconvex and nonsmooth optimization. In particular, we consider in this paper some constrained nonconvex optimization models in block decision variables, with or without coupled affine constraints. In the absence of coupled constraints, we show a sublinear rate of convergence to an $$\epsilon $$ ϵ -stationary solution in the form of variational inequality for a generalized conditional gradient method, where the convergence rate is dependent on the Hölderian continuity of the gradient of the smooth part of the objective. For the model with coupled affine constraints, we introduce corresponding $$\epsilon $$ ϵ -stationarity conditions, and apply two proximal-type variants of the ADMM to solve such a model, assuming the proximal ADMM updates can be implemented for all the block variables except for the last block, for which either a gradient step or a majorization–minimization step is implemented. We show an iteration complexity bound of $$O(1/\epsilon ^2)$$ O ( 1 / ϵ 2 ) to reach an $$\epsilon $$ ϵ -stationary solution for both algorithms. Moreover, we show that the same iteration complexity of a proximal BCD method follows immediately. Numerical results are provided to illustrate the efficacy of the proposed algorithms for tensor robust PCA and tensor sparse PCA problems.

Keywords: Structured nonconvex optimization; $$\epsilon $$ ϵ -Stationary; Iteration complexity; Conditional gradient method; Alternating direction method of multipliers; Block coordinate descent method; 90C26; 90C06; 90C60 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (11)

Downloads: (external link)
http://link.springer.com/10.1007/s10589-018-0034-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:coopap:v:72:y:2019:i:1:d:10.1007_s10589-018-0034-y

Ordering information: This journal article can be ordered from
http://www.springer.com/math/journal/10589

DOI: 10.1007/s10589-018-0034-y

Access Statistics for this article

Computational Optimization and Applications is currently edited by William W. Hager

More articles in Computational Optimization and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().