English

MC$^2$: Monte Carlo Correction for Fast Elliptic PDE Solving

Machine Learning 2026-05-12 v1 Artificial Intelligence Computational Engineering, Finance, and Science Computer Vision and Pattern Recognition Numerical Analysis Numerical Analysis

Abstract

Partial differential equation (PDE) solvers underpin scientific computing, but real-world deployment is bounded by compute. Classical Monte Carlo solvers such as Walk-on-Spheres (WoS) are unbiased and geometry-agnostic but are slow. Learned solvers are fast but biased and brittle under distribution shift. We present \textbf{MC2^2}, a hybrid WoS-Neural Network (WoS-NN) PDE solver that treats a low-budget Monte Carlo solution as a structured estimator of the true field and learns a single-pass neural correction to recover a high-fidelity solution. MC2^2 matches the accuracy of solutions using over 1000×1000\times more Monte Carlo compute, outperforming all evaluated classical, denoising, and neural-operator baselines. To enable reproducible study of finite-compute PDE solving, we additionally release \textbf{PDEZoo}, the largest standardized elliptic PDE benchmark to date: 2M PDEs spanning five elliptic families and unlimited geometric compositions, with analytic ground truth and multi-budget Monte Carlo trajectories. Together \textbf{MC2^2} and \textbf{PDEZoo} (1) empirically establish that finite-sample Monte Carlo error is structured, learnable, and correctable in a single forward pass, (2) show that we can solve PDEs \sim\textbf{1000x} faster than with just WoS, and (3) provide the evaluation infrastructure the field has so far lacked.

Cite

@article{arxiv.2605.09288,
  title  = {MC$^2$: Monte Carlo Correction for Fast Elliptic PDE Solving},
  author = {Ethan Hsu and Hong Meng Yam and Ivan Ge},
  journal= {arXiv preprint arXiv:2605.09288},
  year   = {2026}
}
R2 v1 2026-07-01T13:01:09.185Z