Approximation of Functions on Manifolds in High Dimension from Noisy Scattered Data

by   Shira Faigenbaum-Golovin, et al.

In this paper, we consider the fundamental problem of approximation of functions on a low-dimensional manifold embedded in a high-dimensional space, with noise affecting both in the data and values of the functions. Due to the curse of dimensionality, as well as to the presence of noise, the classical approximation methods applicable in low dimensions are less effective in the high-dimensional case. We propose a new approximation method that leverages the advantages of the Manifold Locally Optimal Projection (MLOP) method (introduced by Faigenbaum-Golovin and Levin in 2020) and the strengths of the method of Radial Basis Functions (RBF). The method is parametrization free, requires no knowledge regarding the manifold's intrinsic dimension, can handle noise and outliers in both the function values and in the location of the data, and is applied directly in the high dimensions. We show that the complexity of the method is linear in the dimension of the manifold and squared-logarithmic in the dimension of the codomain of the function. Subsequently, we demonstrate the effectiveness of our approach by considering different manifold topologies and show the robustness of the method to various noise levels.


page 1

page 2

page 3

page 4


Manifold Repairing, Reconstruction and Denoising from Scattered Data in High-Dimension

We consider a problem of great practical interest: the repairing and rec...

Manifold Reconstruction and Denoising from Scattered Data in High Dimension via a Generalization of L_1-Median

In this paper, we present a method for denoising and reconstruction of l...

Learning multivariate functions with low-dimensional structures using polynomial bases

In this paper we study the multivariate ANOVA decomposition for function...

Active Manifolds: A non-linear analogue to Active Subspaces

We present an approach to analyze C^1(R^m) functions that addresses limi...

Manifold Approximation by Moving Least-Squares Projection (MMLS)

In order to avoid the curse of dimensionality, frequently encountered in...

Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbours

We study the approximate nearest neighbour method for cost-sensitive cla...

Unrolling Swiss Cheese: Metric repair on manifolds with holes

For many machine learning tasks, the input data lie on a low-dimensional...

Please sign up or login with your details

Forgot password? Click here to reset