Optimal Convex Lifted Sparse Phase Retrieval and PCA With an Atomic Matrix Norm Regularizer | IEEE Journals & Magazine | IEEE Xplore

Optimal Convex Lifted Sparse Phase Retrieval and PCA With an Atomic Matrix Norm Regularizer


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 ...Show More

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.
Published in: IEEE Transactions on Information Theory ( Volume: 69, Issue: 3, March 2023)
Page(s): 1866 - 1882
Date of Publication: 14 December 2022

ISSN Information:

Funding Agency:


References

References is not available for this document.