Learning manifolds with k-means and k-flats

Learning manifolds with k-means and k-flats

We study the problem of estimating a manifold from random samples. In particular, we consider piecewise constant and piecewise linear estimators induced by k-means and k-flats, and analyze their performance. We extend previous results for k-means in two separate directions. First, we provide new resu...

Full description

Bibliographic Details
Main Authors: Canas, Guillermo D., Poggio, Tomaso A., Rosasco, Lorenzo Andrea
Other Authors: Massachusetts Institute of Technology. Center for Biological & Computational Learning
Format: Article
Language:en_US
Published: Neural Information Processing Systems Foundation 2014
Online Access:http://hdl.handle.net/1721.1/92317
https://orcid.org/0000-0002-3944-0455
https://orcid.org/0000-0001-6376-4786

Internet

http://hdl.handle.net/1721.1/92317
https://orcid.org/0000-0002-3944-0455
https://orcid.org/0000-0001-6376-4786

Similar Items