Simultaneous diagonalization: the asymmetric, low-rank, and noisy settings
Numerical Analysis
2015-05-12 v2
Abstract
Simultaneous matrix diagonalization is used as a subroutine in many machine learning problems, including blind source separation and paramater estimation in latent variable models. Here, we extend algorithms for performing joint diagonalization to low-rank and asymmetric matrices, and we also provide extensions to the perturbation analysis of these methods. Our results allow joint diagonalization to be applied in several new settings.
Cite
@article{arxiv.1501.06318,
title = {Simultaneous diagonalization: the asymmetric, low-rank, and noisy settings},
author = {Volodymyr Kuleshov and Arun Tesjavi Chaganty and Percy Liang},
journal= {arXiv preprint arXiv:1501.06318},
year = {2015}
}