Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage

arXiv1702.06838MaRDI QIDQ6283495FDOQ6283495

Authors: Alp Yurtsever, Madeleine Udell, Joel A. Tropp, Volkan Cevher 

Publication date: 22 February 2017

Abstract: This paper concerns a fundamental class of convex matrix optimization problems. It presents the first algorithm that uses optimal storage and provably computes a low-rank approximation of a solution. In particular, when all solutions have low rank, the algorithm converges to a solution. This algorithm, SketchyCGM, modifies a standard convex optimization scheme, the conditional gradient method, to store only a small randomized sketch of the matrix variable. After the optimization terminates, the algorithm extracts a low-rank approximation of the solution from the sketch. In contrast to nonconvex heuristics, the guarantees for SketchyCGM do not rely on statistical models for the problem data. Numerical work demonstrates the benefits of SketchyCGM over heuristics.

Has companion code repository: https://github.com/dseuss/pyscgm

This page was built for publication: Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6283495)