Non-Gaussian Component Analysis with Log-Density Gradient Estimation
Abstract
Non-Gaussian component analysis (NGCA) is aimed at identifying a linear subspace such that the projected data follows a non-Gaussian distribution. In this paper, we propose a novel NGCA algorithm based on log-density gradient estimation. Unlike existing methods, the proposed NGCA algorithm identifies the linear subspace by using the eigenvalue decomposition without any iterative procedures, and thus is computationally reasonable. Furthermore, through theoretical analysis, we prove that the identified subspace converges to the true subspace at the optimal parametric rate. Finally, the practical performance of the proposed algorithm is demonstrated on both artificial and benchmark datasets.
Cite
Text
Sasaki et al. "Non-Gaussian Component Analysis with Log-Density Gradient Estimation." International Conference on Artificial Intelligence and Statistics, 2016.Markdown
[Sasaki et al. "Non-Gaussian Component Analysis with Log-Density Gradient Estimation." International Conference on Artificial Intelligence and Statistics, 2016.](https://mlanthology.org/aistats/2016/sasaki2016aistats-non/)BibTeX
@inproceedings{sasaki2016aistats-non,
title = {{Non-Gaussian Component Analysis with Log-Density Gradient Estimation}},
author = {Sasaki, Hiroaki and Niu, Gang and Sugiyama, Masashi},
booktitle = {International Conference on Artificial Intelligence and Statistics},
year = {2016},
pages = {1177-1185},
url = {https://mlanthology.org/aistats/2016/sasaki2016aistats-non/}
}