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...
Main Authors: | Canas, Guillermo D. (Contributor), Poggio, Tomaso A. (Contributor), Rosasco, Lorenzo Andrea (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Center for Biological & Computational Learning (Contributor), Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences (Contributor), McGovern Institute for Brain Research at MIT (Contributor) |
Format: | Article |
Language: | English |
Published: |
Neural Information Processing Systems Foundation,
2014-12-16T14:51:47Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
On invariance and selectivity in representation learning
by: Anselmi, Fabio, et al.
Published: (2017) -
Flat manifolds
by: Symonds, P. A.
Published: (1984) -
K-harmonic manifolds
by: Hadi, Kamal El
Published: (1970) -
Convex learning of multiple tasks and their structure
by: Ciliberto, Carlo, et al.
Published: (2017) -
Foliation by constant mean curvature surfaces in asymptotically flat manifolds
Published: (2014)