Neural Control Variates with Automatic Integration
Open Access
- 13 July 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Abstract
This paper presents a method to leverage arbitrary neural network architecture for control variates. Control variates are crucial in reducing the variance of Monte Carlo integration, but they hinge on finding a function that both correlates with the integrand and has a known analytical integral. Traditional approaches rely on heuristics to choose this function, which might not be expressive enough to correlate well with the integrand. Recent research alleviates this issue by modeling the integrands with a learnable parametric model, such as a neural network. However, the challenge remains in creating an expressive parametric model with a known analytical integral. This paper proposes a novel approach to construct learnable parametric control variates functions from arbitrary neural network architectures. Instead of using a network to approximate the integrand directly, we employ the network to approximate the anti-derivative of the integrand. This allows us to use automatic differentiation to create a function whose integration can be constructed by the antiderivative network. We apply our method to solve partial differential equations using the Walk-on-sphere algorithm [Sawhney and Crane 2020]. Our results indicate that this approach is unbiased using various network architectures and achieves lower variance than other control variate methods.Keywords
All Related Versions
Funding Information
- Army Research Laboratory (W911NF-21-2-0104)
- NSF (National Science Foundation) (IIS-2144117)
This publication has 27 references indexed in Scilit:
- Multi-variable integration with a neural networkJournal of High Energy Physics, 2023
- Modulated Periodic Activations for Generalizable Local Functional Representations2021
- AutoInt: Automatic Integration for Fast Neural Volume Rendering2021
- Neural Control Variates for Monte Carlo Variance Reduction2020
- Spectral and decomposition tracking for rendering heterogeneous volumesACM Transactions on Graphics, 2017
- Image-space control variates for renderingACM Transactions on Graphics, 2016
- Globally Adaptive Control Variate for Robust Numerical IntegrationSIAM Journal on Scientific Computing, 2014
- Robust fairing via conformal curvature flowACM Transactions on Graphics, 2013
- A Family of Nonparametric Density Estimation AlgorithmsCommunications on Pure and Applied Mathematics, 2012
- The problem of integration in finite termsTransactions of the American Mathematical Society, 1969