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

06/03/2021
by   Alden Green, et al.
0

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, and a goodness-of-fit test also based on f. These upper bounds match the minimax optimal estimation and testing rates of convergence over the first-order Sobolev class H^1(𝒳), for 𝒳⊆ℝ^d and 1 ≤ d < 4; in the estimation problem, for d = 4, they are optimal modulo a log n factor. Additionally, we prove that Laplacian smoothing is manifold-adaptive: if 𝒳⊆ℝ^d is an m-dimensional manifold with m < d, then the error rate of Laplacian smoothing (in either estimation or testing) depends only on m, in the same way it would if 𝒳 were a full-dimensional set in ℝ^d.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/14/2021

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

In this paper we study the statistical properties of Principal Component...
research
02/05/2019

Optimal Nonparametric Inference via Deep Neural Network

Deep neural network is a state-of-art method in modern science and techn...
research
09/06/2022

Rates of Convergence for Regression with the Graph Poly-Laplacian

In the (special) smoothing spline problem one considers a variational pr...
research
04/21/2021

Optimal Bayesian Smoothing of Functional Observations over a Large Graph

In modern contexts, some types of data are observed in high-resolution, ...
research
05/25/2018

How Many Machines Can We Use in Parallel Computing for Kernel Ridge Regression?

This paper attempts to solve a basic problem in distributed statistical ...
research
05/26/2016

Total Variation Classes Beyond 1d: Minimax Rates, and the Limitations of Linear Smoothers

We consider the problem of estimating a function defined over n location...
research
12/23/2011

Minimax Rates for Homology Inference

Often, high dimensional data lie close to a low-dimensional submanifold ...

Please sign up or login with your details

Forgot password? Click here to reset