On the Convergence of Maximum Variance Unfolding
Abstract
Maximum Variance Unfolding is one of the main methods for (nonlinear) dimensionality reduction. We study its large sample limit, providing specific rates of convergence under standard assumptions. We find that it is consistent when the underlying submanifold is isometric to a convex subset, and we provide some simple examples where it fails to be consistent.
Cite
Text
Arias-Castro and Pelletier. "On the Convergence of Maximum Variance Unfolding." Journal of Machine Learning Research, 2013.Markdown
[Arias-Castro and Pelletier. "On the Convergence of Maximum Variance Unfolding." Journal of Machine Learning Research, 2013.](https://mlanthology.org/jmlr/2013/ariascastro2013jmlr-convergence/)BibTeX
@article{ariascastro2013jmlr-convergence,
title = {{On the Convergence of Maximum Variance Unfolding}},
author = {Arias-Castro, Ery and Pelletier, Bruno},
journal = {Journal of Machine Learning Research},
year = {2013},
pages = {1747-1770},
volume = {14},
url = {https://mlanthology.org/jmlr/2013/ariascastro2013jmlr-convergence/}
}