Open Access
2016 A spectral series approach to high-dimensional nonparametric regression
Ann B. Lee, Rafael Izbicki
Electron. J. Statist. 10(1): 423-463 (2016). DOI: 10.1214/16-EJS1112


A key question in modern statistics is how to make fast and reliable inferences for complex, high-dimensional data. While there has been much interest in sparse techniques, current methods do not generalize well to data with nonlinear structure. In this work, we present an orthogonal series estimator for predictors that are complex aggregate objects, such as natural images, galaxy spectra, trajectories, and movies. Our series approach ties together ideas from manifold learning, kernel machine learning, and Fourier methods. We expand the unknown regression on the data in terms of the eigenfunctions of a kernel-based operator, and we take advantage of orthogonality of the basis with respect to the underlying data distribution, $P$, to speed up computations and tuning of parameters. If the kernel is appropriately chosen, then the eigenfunctions adapt to the intrinsic geometry and dimension of the data. We provide theoretical guarantees for a radial kernel with varying bandwidth, and we relate smoothness of the regression function with respect to $P$ to sparsity in the eigenbasis. Finally, using simulated and real-world data, we systematically compare the performance of the spectral series approach with classical kernel smoothing, k-nearest neighbors regression, kernel ridge regression, and state-of-the-art manifold and local regression methods.


Download Citation

Ann B. Lee. Rafael Izbicki. "A spectral series approach to high-dimensional nonparametric regression." Electron. J. Statist. 10 (1) 423 - 463, 2016.


Received: 1 June 2015; Published: 2016
First available in Project Euclid: 24 February 2016

zbMATH: 1332.62133
MathSciNet: MR3466189
Digital Object Identifier: 10.1214/16-EJS1112

Primary: 62G08

Keywords: data-driven basis , eigenmaps , high-dimensional inference , manifold learning , Mercer kernel , orthogonal series regression

Rights: Copyright © 2016 The Institute of Mathematical Statistics and the Bernoulli Society

Vol.10 • No. 1 • 2016
Back to Top