Open Access
2015 Tight minimax rates for manifold estimation under Hausdorff loss
Arlene K. H. Kim, Harrison H. Zhou
Electron. J. Statist. 9(1): 1562-1582 (2015). DOI: 10.1214/15-EJS1039

Abstract

This paper deals with minimax rates of convergence for manifold estimation. A new lower bound is obtained by a novel construction of two sets of manifolds and an application of convex hull testing method of Le Cam (1973). The minimax lower bound matches the upper bound up to a constant factor considered by Genovese et al. (2012b).

Citation

Download Citation

Arlene K. H. Kim. Harrison H. Zhou. "Tight minimax rates for manifold estimation under Hausdorff loss." Electron. J. Statist. 9 (1) 1562 - 1582, 2015. https://doi.org/10.1214/15-EJS1039

Information

Received: 1 November 2013; Published: 2015
First available in Project Euclid: 23 July 2015

zbMATH: 1325.62111
MathSciNet: MR3376117
Digital Object Identifier: 10.1214/15-EJS1039

Subjects:
Primary: 62C25 , 62G86
Secondary: 65C50

Keywords: convex hull testing , manifold estimation , minimax lower bound

Rights: Copyright © 2015 The Institute of Mathematical Statistics and the Bernoulli Society

Vol.9 • No. 1 • 2015
Back to Top