227

Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs

International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
Abstract

In this paper we study the statistical properties of Laplacian smoothing, a graph-based approach to nonparametric regression. Under standard regularity conditions, we establish upper bounds on the error of the Laplacian smoothing estimator f^\widehat{f}, and a goodness-of-fit test also based on f^\widehat{f}. These upper bounds match the minimax optimal estimation and testing rates of convergence over the first-order Sobolev class H1(X)H^1(\mathcal{X}), for XRd\mathcal{X}\subseteq \mathbb{R}^d and 1d<41 \leq d < 4; in the estimation problem, for d=4d = 4, they are optimal modulo a logn\log n factor. Additionally, we prove that Laplacian smoothing is manifold-adaptive: if XRd\mathcal{X} \subseteq \mathbb{R}^d is an mm-dimensional manifold with m<dm < d, then the error rate of Laplacian smoothing (in either estimation or testing) depends only on mm, in the same way it would if X\mathcal{X} were a full-dimensional set in Rd\mathbb{R}^d.

View on arXiv
Comments on this paper