Deterministic Independent Component Analysis

Ruitong Huang, Andras Gyorgy, Csaba Szepesvári
Proceedings of the 32nd International Conference on Machine Learning, PMLR 37:2521-2530, 2015.

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/\sqrtT 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 this Paper

BibTeX
@InProceedings{pmlr-v37-huangb15, title = {Deterministic Independent Component Analysis}, author = {Huang, Ruitong and Gyorgy, Andras and Szepesvári, Csaba}, booktitle = {Proceedings of the 32nd International Conference on Machine Learning}, pages = {2521--2530}, year = {2015}, editor = {Bach, Francis and Blei, David}, volume = {37}, series = {Proceedings of Machine Learning Research}, address = {Lille, France}, month = {07--09 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v37/huangb15.pdf}, url = {https://proceedings.mlr.press/v37/huangb15.html}, 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/\sqrtT 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.} }
Endnote
%0 Conference Paper %T Deterministic Independent Component Analysis %A Ruitong Huang %A Andras Gyorgy %A Csaba Szepesvári %B Proceedings of the 32nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2015 %E Francis Bach %E David Blei %F pmlr-v37-huangb15 %I PMLR %P 2521--2530 %U https://proceedings.mlr.press/v37/huangb15.html %V 37 %X 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/\sqrtT 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.
RIS
TY - CPAPER TI - Deterministic Independent Component Analysis AU - Ruitong Huang AU - Andras Gyorgy AU - Csaba Szepesvári BT - Proceedings of the 32nd International Conference on Machine Learning DA - 2015/06/01 ED - Francis Bach ED - David Blei ID - pmlr-v37-huangb15 PB - PMLR DP - Proceedings of Machine Learning Research VL - 37 SP - 2521 EP - 2530 L1 - http://proceedings.mlr.press/v37/huangb15.pdf UR - https://proceedings.mlr.press/v37/huangb15.html AB - 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/\sqrtT 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. ER -
APA
Huang, R., Gyorgy, A. & Szepesvári, C.. (2015). Deterministic Independent Component Analysis. Proceedings of the 32nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 37:2521-2530 Available from https://proceedings.mlr.press/v37/huangb15.html.

Related Material