Research reports

Years: 2026 2025 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 2009 2008 2007 2006 2005 2004 2003 2002 2001 2000 1999 1998 1997 1996 1995 1994 1993 1992 1991

Neural Shape Operator Surrogates Expression Rate Bounds

by H. Harbrecht and Ch. Schwab

(Report number 2026-14)

Abstract
We prove error bounds for operator surrogates of solution operators for partial differential and boundary integral equations on families of domains which are diffeomorphic to one common reference (or latent) domain \(\mathrm{D}\). The pullback of the PDE to \(\mathrm{D}\) via affine-parametric shape encoding produces a collection of holomorphic parametric PDEs on \(\mathrm{D}\). Sufficient conditions for (uniformly with respect to the parameter) well-posedness are given, implying existence, uniqueness and stability of parametric solution families on \(\mathrm{D}\). We illustrate the abstract hypotheses by reviewing recent holomorphy results for a suite of elliptic and parabolic PDEs. Quantified parametric holomorphy implies existence of finiteparametric, discrete approximations of the parametric solution families with convergence rates in terms of the number \(N\) of parameters. We obtain constructive proofs of existence of Neural and Spectral Operator surrogates for the shape-to-solution maps with error bounds and convergence rate guarantees uniform on the collection of admissible shapes. We admit principal-component shape encoders and frame decoders. Our results support in particular the (empirically reported) ability of neural operators to realize data-to-solution maps for elliptic and parabolic PDEs and BIEs that generalize across parametric families of shapes.

Keywords:

@Techreport{HS26_1169,
  author = {H. Harbrecht and Ch. Schwab},
  title = {Neural Shape Operator Surrogates Expression Rate Bounds},
  institution = {Seminar for Applied Mathematics, ETH Z{\"u}rich},
  number = {2026-14},
  address = {Switzerland},
  url = {https://www.sam.math.ethz.ch/sam_reports/reports_final/reports2026/2026-14.pdf },
  year = {2026}
}

Disclaimer
© Copyright for documents on this server remains with the authors. Copies of these documents made by electronic or mechanical means including information storage and retrieval systems, may only be employed for personal use. The administrators respectfully request that authors inform them when any paper is published to avoid copyright infringement. Note that unauthorised copying of copyright material is illegal and may lead to prosecution. Neither the administrators nor the Seminar for Applied Mathematics (SAM) accept any liability in this respect. The most recent version of a SAM report may differ in formatting and style from published journal version. Do reference the published version if possible (see SAM Publications).