Towards optimal sampling for learning sparse approximation in high dimensions

02/04/2022
by   Ben Adcock, et al.
0

In this chapter, we discuss recent work on learning sparse approximations to high-dimensional functions on data, where the target functions may be scalar-, vector- or even Hilbert space-valued. Our main objective is to study how the sampling strategy affects the sample complexity – that is, the number of samples that suffice for accurate and stable recovery – and to use this insight to obtain optimal or near-optimal sampling procedures. We consider two settings. First, when a target sparse representation is known, in which case we present a near-complete answer based on drawing independent random samples from carefully-designed probability measures. Second, we consider the more challenging scenario when such representation is unknown. In this case, while not giving a full answer, we describe a general construction of sampling measures that improves over standard Monte Carlo sampling. We present examples using algebraic and trigonometric polynomials, and for the former, we also introduce a new procedure for function approximation on irregular (i.e., nontensorial) domains. The effectiveness of this procedure is shown through numerical examples. Finally, we discuss a number of structured sparsity models, and how they may lead to better approximations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/04/2019

Optimal sampling strategies for multivariate function approximation on general domains

In this paper, we address the problem of approximating a multivariate fu...
research
01/31/2022

An Adaptive sampling and domain learning strategy for multivariate function approximation on unknown domains

Many problems in computational science and engineering can be described ...
research
06/01/2023

CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions

We introduce a general framework for active learning in regression probl...
research
08/18/2022

Is Monte Carlo a bad sampling strategy for learning smooth functions in high dimensions?

This paper concerns the approximation of smooth, high-dimensional functi...
research
03/25/2022

On efficient algorithms for computing near-best polynomial approximations to high-dimensional, Hilbert-valued functions from limited samples

Sparse polynomial approximation has become indispensable for approximati...
research
05/29/2023

Optimal approximation of infinite-dimensional holomorphic functions

Over the last decade, approximating functions in infinite dimensions fro...
research
11/14/2019

Predicting sparse circle maps from their dynamics

The problem of identifying a dynamical system from its dynamics is of gr...

Please sign up or login with your details

Forgot password? Click here to reset