Loading web-font TeX/Main/Regular
Fast Quadratic Sensing Via Nonconvex Optimization | IEEE Conference Publication | IEEE Xplore

Fast Quadratic Sensing Via Nonconvex Optimization


Abstract:

This paper concerns the problem of recovering an unknown but rank-r signal from quadratic measurements. We formulate the recovery problem as two-stage nonconvex optimizat...Show More

Abstract:

This paper concerns the problem of recovering an unknown but rank-r signal from quadratic measurements. We formulate the recovery problem as two-stage nonconvex optimization approach where an efficient adaptive accelerated gradient-like iterative refinement starting from a careful initialization. Moreover, an efficient initial scheme is proposed for this problem. The average relative error of our initialization estimator reduces exponentially as the oversampling ratio grows, which can also boost the performance of existing two-stage approach for rank--r matrix recovery from vector measurements. Experimental results not only clearly demonstrate the superiority of introduced initialization estimator but also show the advantages of our adaptive accelerated gradient-like approach in terms of both sample complexity and computational complexity.
Date of Conference: 29 August 2022 - 02 September 2022
Date Added to IEEE Xplore: 18 October 2022
ISBN Information:

ISSN Information:

Conference Location: Belgrade, Serbia

Funding Agency:


References

References is not available for this document.