Approximation of Functions over Manifolds: A Moving Least-Squares Approach

11/02/2017
by   Barak Sober, et al.
0

We present an algorithm for approximating a function defined over a d-dimensional manifold utilizing only noisy function values at locations sampled from the manifold with noise. To produce the approximation we do not require any knowledge regarding the manifold other than its dimension d. The approximation scheme is based upon the Manifold Moving Least-Squares (MMLS). The proposed algorithm is resistant to noise in both the domain and function values. Furthermore, the approximant is shown to be smooth and of approximation order of O(h^m+1) for non-noisy data, where h is the mesh size with respect to the manifold domain, and m is the degree of a local polynomial approximation utilized in our algorithm. In addition, the proposed algorithm is linear in time with respect to the ambient-space's dimension. Thus, in case of extremely large ambient space dimension, we are able to avoid the curse of dimensionality without having to perform non-linear dimension reduction, which inevitably introduces distortions to the manifold data. We compare, using numerical experiments, the presented algorithm to state-of-the-art algorithms for regression over manifolds and show its potential.

READ FULL TEXT
research
06/22/2016

Manifold Approximation by Moving Least-Squares Projection (MMLS)

In order to avoid the curse of dimensionality, frequently encountered in...
research
06/13/2020

Sample complexity and effective dimension for regression on manifolds

We consider the theory of regression on a manifold using reproducing ker...
research
08/01/2019

Deep Gaussian networks for function approximation on data defined manifolds

In much of the literature on function approximation by deep networks, th...
research
08/02/2019

Deep ReLU network approximation of functions on a manifold

Whereas recovery of the manifold from data is a well-studied topic, appr...
research
04/30/2019

Active Manifolds: A non-linear analogue to Active Subspaces

We present an approach to analyze C^1(R^m) functions that addresses limi...
research
10/04/2021

A manifold learning approach for gesture identification from micro-Doppler radar measurements

A recent paper (Neural Networks, 132 (2020), 253-268) introduces a strai...
research
12/23/2022

Your diffusion model secretly knows the dimension of the data manifold

In this work, we propose a novel framework for estimating the dimension ...

Please sign up or login with your details

Forgot password? Click here to reset