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

DevFeed: [MC$^2$: Monte Carlo Correction for Fast Elliptic PDE Solving](<https://devfeed.tech/articles/mc-2-monte-carlo-correction-for-fast-elliptic-pde-solving-128102.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.09288>)

Author: Ethan Hsu, Hong Meng Yam, Ivan Ge

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [computer-graphics](<https://devfeed.tech/tags/computer-graphics.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ce](<https://devfeed.tech/tags/cs-ce.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-na](<https://devfeed.tech/tags/cs-na.md>), [data](<https://devfeed.tech/tags/data.md>), [elliptic](<https://devfeed.tech/tags/elliptic.md>), [error-correction](<https://devfeed.tech/tags/error-correction.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [fast](<https://devfeed.tech/tags/fast.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [math-na](<https://devfeed.tech/tags/math-na.md>), [monte-carlo](<https://devfeed.tech/tags/monte-carlo.md>), [neural](<https://devfeed.tech/tags/neural.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [pass](<https://devfeed.tech/tags/pass.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [release](<https://devfeed.tech/tags/release.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [scientific-computing](<https://devfeed.tech/tags/scientific-computing.md>)

## AI overview

MC$^2$ combines a low-budget Walk-on-Spheres Monte Carlo estimate with a single-pass neural correction to produce higher-fidelity elliptic PDE solutions. The authors report accuracy matching solutions based on over 1,000 times as many Monte Carlo samples, and about 218 times faster solving than WoS at matched accuracy. Against state-of-the-art diffusion methods, they report about 171 times lower inference time while achieving higher accuracy. These are reported experimental comparisons; the excerpt does not specify their evaluation conditions. The accompanying PDEZoo benchmark contains 2 million PDEs across five elliptic families, with analytic ground truth and multi-budget Monte Carlo trajectories, intended to support reproducible evaluation.

## Source excerpt

arXiv:2605.09288v2 Announce Type: replace-cross Abstract: Partial differential equation (PDE) solvers underpin modern computer graphics, geometry processing, and scientific computing. Classical Monte Carlo PDE solvers such as Walk-on-Spheres (WoS) provide mesh-free estimations that are unbiased, but with accuracy limited by sampling and numerical approximation. Learned solvers are fast but biased and brittle under distribution shift. We therefore present MC$^2$, a hybrid Neural Network-Monte Carlo 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. MC$^2$ matches the accuracy of solutions using over $1000\times$ more Monte Carlo samples, outperforming all evaluated mesh-free classical, denoising, and neural-operator baselines. To enable reproducible study of finite-compute PDE solving, we additionally release PDEZoo, the largest standardized elliptic PDE benchmark to date: 2 million PDEs spanning 5 elliptic families and unlimited geometric compositions, with analytic ground truth and multi-budget Monte Carlo trajectories. Together, MC$^2$ and 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$218$\times$ faster than WoS at matched accuracy and achieve a $\sim$171$\times$ reduction in inference time relative to state-of-the-art diffusion methods while attaining higher accuracy, and (3) provide the reproducible evaluation infrastructure the field has so far lacked. Code & Data: https://mc-error-correction.github.io