Mean dimension of radial basis functions

02/19/2023
by   Christopher Hoyt, et al.
0

We show that generalized multiquadric radial basis functions (RBFs) on ℝ^d have a mean dimension that is 1+O(1/d) as d→∞ with an explicit bound for the implied constant, under moment conditions on their inputs. Under weaker moment conditions the mean dimension still approaches 1. As a consequence, these RBFs become essentially additive as their dimension increases. Gaussian RBFs by contrast can attain any mean dimension between 1 and d. We also find that a test integrand due to Keister that has been influential in quasi-Monte Carlo theory has a mean dimension that oscillates between approximately 1 and approximately 2 as the nominal dimension d increases.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2019

Direct Sampling of Bayesian Thin-Plate Splines for Spatial Smoothing

Radial basis functions are a common mathematical tool used to construct ...
research
07/02/2020

Efficient estimation of the ANOVA mean dimension, with an application to neural net classification

The mean dimension of a black box function of d variables is a convenien...
research
07/01/2019

Mean Dimension of Ridge Functions

We consider the mean dimension of some ridge functions of spherical Gaus...
research
09/06/2023

New methods for quasi-interpolation approximations: resolution of odd-degree singularities

In this paper, we study functional approximations where we choose the so...
research
01/17/2019

Double variational principle for mean dimension with potential

This paper contributes to the mean dimension theory of dynamical systems...
research
01/17/2019

Double variational principle for mean dimension

We develop a variational principle between mean dimension theory and rat...
research
09/02/2021

Computation of Power Law Equilibrium Measures on Balls of Arbitrary Dimension

We present a numerical approach for computing attractive-repulsive power...

Please sign up or login with your details

Forgot password? Click here to reset