Learning gradients on manifolds

Abstract

A common belief in high-dimensional data analysis is that data are concentrated on a low-dimensional manifold. This motivates simultaneous dimension reduction and regression on manifolds. We provide an algorithm for learning gradients on manifolds for dimension reduction for high-dimensional data with few observations. We obtain generalization error bounds for the gradient estimates and show that the convergence rate depends on the intrinsic dimension of the manifold and not on the dimension of the ambient space. We illustrate the efficacy of this approach empirically on simulated and real data and compare the method to other dimension reduction procedures.

Published in at http://dx.doi.org/10.3150/09-BEJ206 the Bernoulli (http://isi.cbs.nl/bernoulli/) by the International Statistical Institute/Bernoulli Society (http://isi.cbs.nl/BS/bshome.htm)

References in corpus (2)

• Local polynomial regression on unknown manifolds
• The Use of Unlabeled Data in Predictive Modeling

Cited by in corpus (9)

• When Locally Linear Embedding Hits Boundary
• Gradient Estimation with Simultaneous Perturbation and Compressive Sensing
• On linear hypersingular Boltzmann transport equation and its variational formulation
• Nonlinear generalization of the monotone single index model
• Sensitivity of Regular Estimators
• Local Linear Regression on Manifolds and its Geometric Interpretation
• Convergence of Hessian estimator from random samples on a manifold with boundary
• Random Lie Brackets that Induce Torsion: A Model for Noisy Vector Fields
• Learning sparse gradients for variable selection and dimension reduction