Information-Theoretic Bounds for Integral Estimation

TL;DR

This paper establishes fundamental information-theoretic limits for estimating integrals using noisy oracle queries and evaluates the performance of Gaussian Quadrature within this framework, highlighting gaps for future method improvements.

Contribution

It derives the lower bounds on estimation error and analyzes the optimality of Gaussian Quadrature under a stochastic oracle model for integral estimation.

Findings

Lower bound on estimation error: (2^d r^{d+1}\u221a(d/T))

Gaussian Quadrature achieves near-optimal rate for certain smooth functions

Gaussian Quadrature is not minimax optimal for functions with nonzero fourth derivatives.

Abstract

In this paper, we consider a zero-order stochastic oracle model of estimating definite integrals. In this model, integral estimation methods may query an oracle function for a fixed number of noisy values of the integrand function and use these values to produce an estimate of the integral. We first show that the information-theoretic error lower bound for estimating the integral of a $d$-dimensional function over a region with $l_\infty$ radius $r$ using at most $T$ queries to the oracle function is $\Omega(2^d r^{d+1}\sqrt{d/T})$. Additionally, we find that the Gaussian Quadrature method under the same model achieves a rate of $O(2^{d}r^d/\sqrt{T})$ for functions with zero fourth and higher-order derivatives with respect to individual dimensions, and for Gaussian oracles, this rate is tight. For functions with nonzero fourth derivatives, the Gaussian Quadrature method achieves an upper bound which is not tight with the information-theoretic lower bound. Therefore, it is not minimax optimal, so there is space for the development of better integral estimation methods for such functions.