-

 

 

 




Optimization Online





 

An Extended Frank-Wolfe Method with “In-Face” Directions, and its Application to Low-Rank Matrix Completion

Robert M. Freund(rfreund***at***mit.edu)
Paul Grigas(pgrigas***at***mit.edu)
Rahul Mazumder(rahulmaz***at***mit.edu)

Abstract: 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. We present computational guarantees for the method that trade off efficiency in computing near-optimal solutions with upper bounds on the dimension of minimal faces of iterates. We apply our method to the low-rank matrix completion problem, where low-dimensional faces correspond to low-rank solutions. We present computational results for large-scale low-rank matrix completion problems that demonstrate significant speed-ups in computing low-rank near-optimal solutions on both artificial and real datasets.

Keywords: matrix completion, Frank-Wolfe, conditional gradient, low-rank, nuclear norm, first-order methods

Category 1: Convex and Nonsmooth Optimization (Convex Optimization )

Category 2: Applications -- Science and Engineering (Data-Mining )

Citation: MIT Operations Research Center Working Paper, November, 2015

Download: [PDF]

Entry Submitted: 11/06/2015
Entry Accepted: 11/06/2015
Entry Last Modified: 11/06/2015

Modify/Update this entry


  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository

 

Submit
Update
Policies
Coordinator's Board
Classification Scheme
Credits
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society