The Segal-Bargmann Transform in Neural Partial Differential Equations
Abstract
We introduce a novel neural operator method based on Segal-Bargmann transform and Bargmann-Fock space for learning the solution operators of partial differential equations (PDEs). The method brings data encoding, latent-space representation, operator learning, and decoding into an unifed framework. From only finitely many observations, we establish a sup-norm reconstruction error of order $ L^{-\frac{1}{2}} $, where L is the number of complex sampling points that are decoupled with the original samplings and observations. The reconstruction error is independent of the spatial dimension and the number of original sampling points. We show that this new mesh-free Segal-Bargmann Neural Operator approach has superior performance compared to existing NO approaches like FNO, BelNet, GNOT, etc.,\ particularly in terms of pointwise control $ \sup_{x}\lvert\hat{u}_{NO} - u_{truth}\rvert $ for solutions of PDEs $ \mathcal{L}u = f $ which provides pointwise accuracy and interpretability as classical numerical solvers. We also demonstrates the reconstructions of the solution operators for higher dimensional nonlinear PDEs, which suggest that our proposed method has great potential to be applied to more challenging PDEs and to even higher spatial dimensions.
Related
- Solving Fractional Partial Differential Equations Using the Double Natural Transform Decomposition Method
- AKAPINN: Adaptive Kolmogorov-Arnold Physics-Informed Neural Networks for approximating solutions to quasilinear partial differential equations
- An Adaptive Transferable Neural Network for Partial Differential Equations with Anisotropic or Sharp Solutions
- Cluster Attention Neural Operators for Solving Parametric Partial Differential Equations
- FOSLS-deRhaNN: native de Rham neural classes for H(div) and H(curl) with applications to first-order system least-squares neural network methods for partial differential equations
BibTeX
@misc{xu2026segalbargmann,
title = {{The Segal-Bargmann Transform in Neural Partial Differential Equations}},
author = {Jie Xu and Julio Castrillón-Candás and Mark Kon and Qinxun Bai},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.24497},
eprint = {2610.24497},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.24497},
note = {CC0},
}
RIS
TY - UNPB
TI - The Segal-Bargmann Transform in Neural Partial Differential Equations
AU - Jie Xu
AU - Julio Castrillón-Candás
AU - Mark Kon
AU - Qinxun Bai
PY - 2026
DA - 2026/10/17
PB - arXiv
DO - 10.48550/arxiv.2610.24497
UR - https://arxiv.org/abs/2610.24497
AB - We introduce a novel neural operator method based on Segal-Bargmann transform and Bargmann-Fock space for learning the solution operators of partial differential equations (PDEs). The method brings data encoding, latent-space representation, operator learning, and decoding into an unifed framework. From only finitely many observations, we establish a sup-norm reconstruction error of order $ L^{-\frac{1}{2}} $, where L is the number of complex sampling points that are decoupled with the original samplings and observations. The reconstruction error is independent of the spatial dimension and the number of original sampling points. We show that this new mesh-free Segal-Bargmann Neural Operator approach has superior performance compared to existing NO approaches like FNO, BelNet, GNOT, etc.,\ particularly in terms of pointwise control $ \sup_{x}\lvert\hat{u}_{NO} - u_{truth}\rvert $ for solutions of PDEs $ \mathcal{L}u = f $ which provides pointwise accuracy and interpretability as classical numerical solvers. We also demonstrates the reconstructions of the solution operators for higher dimensional nonlinear PDEs, which suggest that our proposed method has great potential to be applied to more challenging PDEs and to even higher spatial dimensions.
ER -