Local approximation of operators

02/13/2022
∙
by   Hrushikesh Mhaskar, et al.
∙
0
∙

Many applications, such as system identification, classification of time series, direct and inverse problems in partial differential equations, and uncertainty quantification lead to the question of approximation of a non-linear operator between metric spaces 𝔛 and 𝔜. We study the problem of determining the degree of approximation of a such operators on a compact subset K_𝔛⊂𝔛 using a finite amount of information. If ℱ: K_𝔛→ K_𝔜, a well established strategy to approximate ℱ(F) for some F∈ K_𝔛 is to encode F (respectively, ℱ(F)) in terms of a finite number d (repectively m) of real numbers. Together with appropriate reconstruction algorithms (decoders), the problem reduces to the approximation of m functions on a compact subset of a high dimensional Euclidean space ℝ^d, equivalently, the unit sphere 𝕊^d embedded in ℝ^d+1. The problem is challenging because d, m, as well as the complexity of the approximation on 𝕊^d are all large, and it is necessary to estimate the accuracy keeping track of the inter-dependence of all the approximations involved. In this paper, we establish constructive methods to do this efficiently; i.e., with the constants involved in the estimates on the approximation on mathbbS^d being 𝒪(d^1/6). We study different smoothness classes for the operators, and also propose a method for approximation of ℱ(F) using only information in a small neighborhood of F, resulting in an effective reduction in the number of parameters involved. To further mitigate the problem of large number of parameters, we propose prefabricated networks, resulting in a substantially smaller number of effective parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
∙ 03/07/2020

Neural Operator: Graph Kernel Network for Partial Differential Equations

The classical development of neural networks has been primarily for mapp...
research
∙ 12/29/2021

Deep neural network approximation theory for high-dimensional functions

The purpose of this article is to develop machinery to study the capacit...
research
∙ 10/25/2019

Approximation of functions by linear summation methods in the Orlicz type spaces

Approximative properties of linear summation methods of Fourier series a...
research
∙ 12/26/2019

Inverses of Matern Covariances on Grids

We conduct a theoretical and numerical study of the aliased spectral den...
research
∙ 02/10/2022

Sharp L_p-error estimates for sampling operators

We study approximation properties of linear sampling operators in the sp...
research
∙ 03/01/2015

Constructive sparse trigonometric approximation for functions with small mixed smoothness

The paper gives a constructive method, based on greedy algorithms, that ...
research
∙ 05/17/2021

Universal Regular Conditional Distributions

We introduce a general framework for approximating regular conditional d...

Please sign up or login with your details

Forgot password? Click here to reset