Learning Manifolds with K-Means and K-Flats

Part of Advances in Neural Information Processing Systems 25 (NIPS 2012)

Bibtex Metadata Paper Supplemental


Guillermo Canas, Tomaso Poggio, Lorenzo Rosasco


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 results for k-means reconstruction on manifolds and, secondly, we prove reconstruction bounds for higher-order approximation (k-flats), for which no known results were previously available. While the results for k-means are novel, some of the technical tools are well-established in the literature. In the case of k-flats, both the results and the mathematical tools are new.