Deterministic Independent Component Analysis
Abstract
We study independent component analysis with noisy observations. We present, for the first time in the literature, consistent, polynomial-time algorithms to recover non-Gaussian source signals and the mixing matrix with a reconstruction error that vanishes at a 1/\sqrt{T} rate using T observations and scales only polynomially with the natural parameters of the problem. Our algorithms and analysis also extend to deterministic source signals whose empirical distributions are approximately independent.
Cite
Text
Huang et al. "Deterministic Independent Component Analysis." International Conference on Machine Learning, 2015.Markdown
[Huang et al. "Deterministic Independent Component Analysis." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/huang2015icml-deterministic/)BibTeX
@inproceedings{huang2015icml-deterministic,
title = {{Deterministic Independent Component Analysis}},
author = {Huang, Ruitong and Gyorgy, Andras and Szepesvári, Csaba},
booktitle = {International Conference on Machine Learning},
year = {2015},
pages = {2521-2530},
volume = {37},
url = {https://mlanthology.org/icml/2015/huang2015icml-deterministic/}
}