Back to Search Start Over

Optimal convex lifted sparse phase retrieval and PCA with an atomic matrix norm regularizer

Authors :
McRae, Andrew D.
Romberg, Justin
Davenport, Mark A.
Publication Year :
2021

Abstract

We present novel analysis and algorithms for solving sparse phase retrieval and sparse principal component analysis (PCA) with convex lifted matrix formulations. The key innovation is a new mixed atomic matrix norm that, when used as regularization, promotes low-rank matrices with sparse factors. We show that convex programs with this atomic norm as a regularizer provide near-optimal sample complexity and error rate guarantees for sparse phase retrieval and sparse PCA. While we do not know how to solve the convex programs exactly with an efficient algorithm, for the phase retrieval case we carefully analyze the program and its dual and thereby derive a practical heuristic algorithm. We show empirically that this practical algorithm performs similarly to existing state-of-the-art algorithms.

Subjects

Subjects :
Mathematics - Statistics Theory

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2111.04652
Document Type :
Working Paper
Full Text :
https://doi.org/10.1109/TIT.2022.3228508