Painless Breakups -- Efficient Demixing of Low Rank Matrices
arXiv:1703.09848
Abstract
Assume we are given a sum of linear measurements of different rank- matrices of the form . When and under which conditions is it possible to extract (demix) the individual matrices from the single measurement vector ? And can we do the demixing numerically efficiently? We present two computationally efficient algorithms based on hard thresholding to solve this low rank demixing problem. We prove that under suitable conditions these algorithms are guaranteed to converge to the correct solution at a linear rate. We discuss applications in connection with quantum tomography and the Internet-of-Things. Numerical simulations demonstrate empirically the performance of the proposed algorithms.
References in corpus (7)
- Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
- Tight oracle bounds for low-rank matrix recovery from a minimal number of random measurements
- Convexity in source separation: Models, geometry, and algorithms
- Guaranteed recovery of quantum processes from few measurements
- Guarantees of Riemannian Optimization for Low Rank Matrix Completion
- Convolutional Dictionary Learning through Tensor Factorization
- Regularized Gradient Descent: A Nonconvex Recipe for Fast Joint Blind Deconvolution and Demixing