Sparse Harmonic Transforms: A New Class of Sublinear-time Algorithms for Learning Functions of Many Variables

TL;DR

This paper introduces a novel sublinear-time algorithm for learning functions with sparse representations in bounded orthonormal tensor product bases, significantly reducing computational and memory costs for high-dimensional problems.

Contribution

It develops the first sublinear-time, memory-efficient method for sparse function approximation in general BOPB frameworks, enabling scalable high-dimensional UQ applications.

Findings

Runtime of the method is $(s ext{log} N)^{O(1)}$

Uses only $(s ext{log} N)^{O(1)}$ function evaluations

Requires no more than $(s ext{log} N)^{O(1)}$ bits of memory

Abstract

We develop fast and memory efficient numerical methods for learning functions of many variables that admit sparse representations in terms of general bounded orthonormal tensor product bases. Such functions appear in many applications including, e.g., various Uncertainty Quantification(UQ) problems involving the solution of parametric PDE that are approximately sparse in Chebyshev or Legendre product bases. We expect that our results provide a starting point for a new line of research on sublinear-time solution techniques for UQ applications of the type above which will eventually be able to scale to significantly higher-dimensional problems than what are currently computationally feasible. More concretely, let $B$ be a finite Bounded Orthonormal Product Basis (BOPB) of cardinality $|B|=N$. We will develop methods that approximate any function $f$ that is sparse in the BOPB, that is, $f:\mathcal{D}\subset R^D\rightarrow C$ of the form $f(\mathbf{x})=\sum_{b\in S}c_b\cdot b(\mathbf{x})$ with $S\subset B$ of cardinality $|S| =s\ll N$. Our method has a runtime of just $(s\log N)^{O(1)}$, uses only $(s\log N)^{O(1)}$ function evaluations on a fixed and nonadaptive grid, and not more than $(s\log N)^{O(1)}$ bits of memory. For $s\ll N$, the runtime $(s\log N)^{O(1)}$ will be less than what is required to simply enumerate the elements of the basis $B$; thus our method is the first approach applicable in a general BOPB framework that falls into the class referred to as "sublinear-time". This and the similarly reduced sample and memory requirements set our algorithm apart from previous works based on standard compressive sensing algorithms such as basis pursuit which typically store and utilize full intermediate basis representations of size $\Omega(N)$.