Linear Dependent Dimensionality Reduction
Abstract
We formulate linear dimensionality reduction as a semi-parametric esti- mation problem, enabling us to study its asymptotic behavior. We gen- eralize the problem beyond additive Gaussian noise to (unknown) non- Gaussian additive noise, and to unbiased non-additive models.
Cite
Text
Srebro and Jaakkola. "Linear Dependent Dimensionality Reduction." Neural Information Processing Systems, 2003.Markdown
[Srebro and Jaakkola. "Linear Dependent Dimensionality Reduction." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/srebro2003neurips-linear/)BibTeX
@inproceedings{srebro2003neurips-linear,
title = {{Linear Dependent Dimensionality Reduction}},
author = {Srebro, Nathan and Jaakkola, Tommi S.},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {145-152},
url = {https://mlanthology.org/neurips/2003/srebro2003neurips-linear/}
}