Statistics – Machine Learning
Scientific paper
2010-07-04
Statistics
Machine Learning
journal submission, revision with some errors corrected
Scientific paper
We find the minimax rate of convergence in Hausdorff distance for estimating a manifold M of dimension d embedded in R^D given a noisy sample from the manifold. We assume that the manifold satisfies a smoothness condition and that the noise distribution has compact support. 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.
Genovese Christopher
Perone-Pacifico Marco
Verdinelli Isabella
Wasserman Larry
No associations
LandOfFree
Minimax Manifold Estimation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Minimax Manifold Estimation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Minimax Manifold Estimation will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-442963