English

Learning Solution Operators for Partial Differential Equations via Monte Carlo-Type Approximation

Machine Learning 2025-11-25 v1 Artificial Intelligence

Abstract

The Monte Carlo-type Neural Operator (MCNO) introduces a lightweight architecture for learning solution operators for parametric PDEs by directly approximating the kernel integral using a Monte Carlo approach. Unlike Fourier Neural Operators, MCNO makes no spectral or translation-invariance assumptions. The kernel is represented as a learnable tensor over a fixed set of randomly sampled points. This design enables generalization across multiple grid resolutions without relying on fixed global basis functions or repeated sampling during training. Experiments on standard 1D PDE benchmarks show that MCNO achieves competitive accuracy with low computational cost, providing a simple and practical alternative to spectral and graph-based neural operators.

Keywords

Cite

@article{arxiv.2511.18930,
  title  = {Learning Solution Operators for Partial Differential Equations via Monte Carlo-Type Approximation},
  author = {Salah Eddine Choutri and Prajwal Chauhan and Othmane Mazhar and Saif Eddin Jabari},
  journal= {arXiv preprint arXiv:2511.18930},
  year   = {2025}
}

Comments

NeurIPS 2025 Workshop on Machine Learning and the Physical Sciences

R2 v1 2026-07-01T07:51:49.065Z