Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage
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.
Additional Information
© 2017 by the author(s). Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, Fort Lauderdale, Florida, USA. JMLR: W&CP volume 54.Attached Files
Submitted - 1702.06838.pdf
Files
Name | Size | Download all |
---|---|---|
md5:9064e8de45f6f8d5ae68322bef155510
|
1.2 MB | Preview Download |
Additional details
- Eprint ID
- 89263
- Resolver ID
- CaltechAUTHORS:20180828-145534045
- Created
-
2018-08-28Created from EPrint's datestamp field
- Updated
-
2023-06-02Created from EPrint's last_modified field