Learning Manifolds with K-Means and K-Flats

09/05/2012
by   Guillermo D. Canas, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/09/2018

Uniform bounds for robust mean estimators

Median-of-means technique is an elegant and general method for estimatin...
research
06/16/2022

A Bernstein–von-Mises theorem for the Calderón problem with piecewise constant conductivities

This note considers a finite dimensional statistical model for the Calde...
research
12/04/2020

Convergence results for some piecewise linear solvers

Let A be a real n× n matrix and z,b∈ℝ^n. The piecewise linear equation s...
research
10/27/2020

Improved Guarantees for k-means++ and k-means++ Parallel

In this paper, we study k-means++ and k-means++ parallel, the two most p...
research
03/13/2023

On the width of complicated JSJ decompositions

Motivated by the algorithmic study of 3-dimensional manifolds, we explor...
research
05/24/2023

Short and Straight: Geodesics on Differentiable Manifolds

Manifolds discovered by machine learning models provide a compact repres...

Please sign up or login with your details

Forgot password? Click here to reset