Exterior-Point Optimization for Sparse and Low-Rank Optimization
Author(s)
Das Gupta, Shuvomoy; Stellato, Bartolomeo; Van Parys, Bart P. G.
Download10957_2024_2448_ReferencePDF.pdf (1.096Mb)
Publisher Policy
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
Many problems of substantial current interest in machine learning, statistics, and data science can be formulated as sparse and low-rank optimization problems. In this paper, we present the nonconvex exterior-point optimization solver (NExOS)—a first-order algorithm tailored to sparse and low-rank optimization problems. We consider the problem of minimizing a convex function over a nonconvex constraint set, where the set can be decomposed as the intersection of a compact convex set and a nonconvex set involving sparse or low-rank constraints. Unlike the convex relaxation approaches, NExOS finds a locally optimal point of the original problem by solving a sequence of penalized problems with strictly decreasing penalty parameters by exploiting the nonconvex geometry. NExOS solves each penalized problem by applying a first-order algorithm, which converges linearly to a local minimum of the corresponding penalized formulation under regularity conditions. Furthermore, the local minima of the penalized problems converge to a local minimum of the original problem as the penalty parameter goes to zero. We then implement and test NExOS on many instances from a wide variety of sparse and low-rank optimization problems, empirically demonstrating that our algorithm outperforms specialized methods.
Date issued
2024-05-26Department
Massachusetts Institute of Technology. Operations Research CenterJournal
Journal of Optimization Theory and Applications
Publisher
Springer US
Citation
Das Gupta, S., Stellato, B. & Van Parys, B.P.G. Exterior-Point Optimization for Sparse and Low-Rank Optimization. J Optim Theory Appl 202, 795–833 (2024).
Version: Author's final manuscript