An Extended Frank--Wolfe Method with “In-Face” Directions, and Its Application to Low-Rank Matrix Completion
Name
15m104726x.pdf
Size
858.31 KB
Format
Adobe PDF
Checksum (MD5)
9047397f06eaf504363797bb77f91ee0
Author(s)
Grigas, Paul
Freund, Robert Michael
Mazumder, Rahul
Date Issued
March 2017
Journal
SIAM Journal on Optimization
Publisher
Society for Industrial & Applied Mathematics (SIAM)
Citation
Freund, Robert M., et al. “An Extended Frank--Wolfe Method with ‘In-Face’ Directions, and Its Application to Low-Rank Matrix Completion.” SIAM Journal on Optimization, vol. 27, no. 1, Jan. 2017, pp. 319–46. © by SIAM
Version
Final published version
Abstract
Motivated principally by the low-rank matrix completion problem, we present an extension of the Frank-Wolfe method that is designed to induce near-optimal solutions on low- dimensional faces of the feasible region. This is accomplished by a new approach to generating "in-face" directions at each iteration, as well as through new choice rules for selecting between in- face and "regular" Frank-Wolfe steps. Our framework for generating in-face directions generalizes the notion of away steps introduced by Wolfe. In particular, the in-face directions always keep the next iterate within the minimal face containing the current iterate. We present computational guarantees for the new method that trade off efficiency in computing near-optimal solutions with upper bounds on the dimension of minimal faces of iterates. We apply the new method to the matrix completion problem, where low-dimensional faces correspond to low-rank matrices. We present computational results that demonstrate the effectiveness of our methodological approach at producing nearly optimal solutions of very low rank. On both artificial and real datasets, we demonstrate significant speedups in computing very low rank nearly optimal solutions as compared to the Frank-Wolfe method (as well as several of its significant variants). Key words: convex optimization, Frank–Wolfe method, computational guarantees, low-rank, matrix completion, nuclear norm regularization
MIT Department
Sloan School of Management
Terms of Use
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.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1137/15M104726X
