Minimax Manifold Estimation

Abstract

We find the minimax rate of convergence in Hausdorff distance for estimating a manifold M of dimension d embedded in ℝD given a noisy sample from the manifold. Under certain conditions, we show that the optimal rate of convergence is n-2/(2+d). Thus, the minimax rate depends only on the dimension of the manifold, not on the dimension of the space in which M is embedded.

Cite

Text

Genovese et al. "Minimax Manifold Estimation." Journal of Machine Learning Research, 2012.

Markdown

[Genovese et al. "Minimax Manifold Estimation." Journal of Machine Learning Research, 2012.](https://mlanthology.org/jmlr/2012/genovese2012jmlr-minimax/)

BibTeX

@article{genovese2012jmlr-minimax,
  title     = {{Minimax Manifold Estimation}},
  author    = {Genovese, Christopher and Perone-Pacifico, Marco and Verdinelli, Isabella and Wasserman, Larry},
  journal   = {Journal of Machine Learning Research},
  year      = {2012},
  pages     = {1263-1291},
  volume    = {13},
  url       = {https://mlanthology.org/jmlr/2012/genovese2012jmlr-minimax/}
}