Regression-based Monte Carlo Integration

TL;DR

This paper introduces a novel Monte Carlo integration estimator based on a calculus interpretation that uses regression to improve efficiency, outperforming traditional methods with theoretical guarantees and practical validation.

Contribution

It proposes a new regression-based estimator derived from a calculus perspective, providing provable improvements over standard Monte Carlo methods.

Findings

The new estimator is theoretically guaranteed to be better or equal to the conventional Monte Carlo estimator.

Experimental results show improved accuracy on light transport integrals.

The method can be implemented as a simple replacement for standard Monte Carlo integration.

Abstract

Monte Carlo integration is typically interpreted as an estimator of the expected value using stochastic samples. There exists an alternative interpretation in calculus where Monte Carlo integration can be seen as estimating a \emph{constant} function -- from the stochastic evaluations of the integrand -- that integrates to the original integral. The integral mean value theorem states that this \emph{constant} function should be the mean (or expectation) of the integrand. Since both interpretations result in the same estimator, little attention has been devoted to the calculus-oriented interpretation. We show that the calculus-oriented interpretation actually implies the possibility of using a more \emph{complex} function than a \emph{constant} one to construct a more efficient estimator for Monte Carlo integration. We build a new estimator based on this interpretation and relate our estimator to control variates with least-squares regression on the stochastic samples of the integrand. Unlike prior work, our resulting estimator is \emph{provably} better than or equal to the conventional Monte Carlo estimator. To demonstrate the strength of our approach, we introduce a practical estimator that can act as a simple drop-in replacement for conventional Monte Carlo integration. We experimentally validate our framework on various light transport integrals. The code is available at \url{https://github.com/iribis/regressionmc}.