Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs

• URL: http://arxiv.org/abs/2605.10277v1
• Date: Mon, 11 May 2026 09:35:37 GMT
• Title: Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs
• Abstract summary: We study operator learning for solution operators of nonlinear parabolic PDEs based on Duhamel--Picard iteration.<n>We derive implementation-agnostic generalization error bounds that separate the implementation error from the estimation error.<n>We extend the analysis to long-time prediction by rolling out the same learned local model over successive time blocks.
• Score: 6.175503577352742
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Operator learning for partial differential equations (PDEs) aims to learn solution operators on infinite-dimensional function spaces from finite-resolution data. In this setting, it is important for the learned model to be discretization-invariant, or resolution-robust, and to reflect PDE-specific structure. It is therefore natural to ask how such structure should be encoded in the model architecture, hypothesis class, or learning procedure. In this paper, we study operator learning for solution operators of nonlinear parabolic PDEs based on Duhamel--Picard iteration. We formulate Picard iteration as an abstract state-transition model and present a theoretical framework for Picard-type operator learning. We derive implementation-agnostic generalization error bounds that separate the implementation error from the estimation error associated with the abstract state-transition model induced by Picard iteration. A key consequence is that increasing the Picard depth reduces the Picard truncation error without causing an unbounded growth of the entropy-based estimation error. We also extend the analysis to long-time prediction by rolling out the same learned local model over successive time blocks. Finally, we illustrate the theory for nonlinear heat equations on the torus using a Picard-type Fourier neural operator as a concrete implementation.

Related papers

• Equation Recast for Canonical Operator Learning Across Parametric PDEs [59.44573033543284]
  We introduce equation recast, which reformulates parametric operator learning as the learning of a single canonical operator.<n>In high-fidelity tokamak simulations for nuclear fusion, the framework unifies electron-temperature data across four device geometries.
  arXiv  Detail & Related papers  (2026-09-02T13:15:50Z)
• A Zeroth-Order Deep Learning Method for Fully Nonlinear Parabolic Partial Differential Equations with Unknown Coefficients [5.693122506667716]
  High-weighted partial-dimensional differential equations (PDEs) with unknown coefficients arise widely in machine learning.<n>Existing deep learning solvers often rely on repeated automatic differentiation to evaluate differential operators.<n>We introduce two types of simulators as data-generating mechanisms, and take a representing-then-learning" approach that learns the solutions and their derivatives under settings where the underlying PDE operators are accessible.
  arXiv  Detail & Related papers  (2026-06-23T16:04:43Z)
• Approximation Theory of Laplacian-Based Neural Operators for Reaction-Diffusion System [4.86840788259762]
  We study neural operators applied to the solution mapping from initial conditions to time-dependent solutions of a generalized Gierer-Meinhardt-diffusion system.<n>Our main results establish explicit approximation error bounds in terms of network depth, width, and spectral rank.<n>We show that Laplacian eigenfunction-based neural architectures alleviate the curse of parametric complexity encountered in generic operator learning.
  arXiv  Detail & Related papers  (2026-05-12T12:13:04Z)
• GRIFDIR: Graph Resolution-Invariant FEM Diffusion Models in Function Spaces over Irregular Domains [56.121725064621295]
  Score-based diffusion models in function spaces offer a principled framework for modelling function-valued data.<n>However, practical implementations have struggled to fully realise these benefits.<n>We propose a novel architecture that represents generalised convolutional kernels as finite graph kernels.
  arXiv  Detail & Related papers  (2026-05-05T08:33:52Z)
• CompNO: A Novel Foundation Model approach for solving Partial Differential Equations [0.0]
  Partial differential equations govern a wide range of physical phenomena, but their numerical solution remains computationally demanding.<n>Recent Scientific Foundation Models (SFMs) aim to alleviate this cost by learning universal surrogates from large collections of simulated systems.<n>We introduce Compositional Neural Operators (CompNO), a compositional neural operator framework for parametric PDEs.
  arXiv  Detail & Related papers  (2026-01-12T10:04:48Z)
• Scale-Consistent Learning for Partial Differential Equations [79.48661503591943]
  We propose a data augmentation scheme based on scale-consistency properties of PDEs.<n>We then design a scale-informed neural operator that can model a wide range of scales.<n>With scale-consistency, the model trained on $Re$ of 1000 can generalize to $Re$ ranging from 250 to 10000.
  arXiv  Detail & Related papers  (2025-07-24T21:29:52Z)
• A Deep Learning approach for parametrized and time dependent Partial Differential Equations using Dimensionality Reduction and Neural ODEs [46.685771141109306]
  We propose an autoregressive and data-driven method using the analogy with classical numerical solvers for time-dependent, parametric and (typically) nonlinear PDEs.<n>We show that by leveraging DR we can deliver not only more accurate predictions, but also a considerably lighter and faster Deep Learning model.
  arXiv  Detail & Related papers  (2025-02-12T11:16:15Z)
• Physics-Informed Deep Inverse Operator Networks for Solving PDE Inverse Problems [1.9490282165104331]
  Inverse problems involving partial differential equations (PDEs) can be seen as discovering a mapping from measurement data to unknown quantities.<n>Existing methods typically rely on large amounts of labeled training data, which is impractical for most real-world applications.<n>We propose a novel architecture called Physics-Informed Deep Inverse Operator Networks (PI-DIONs) which can learn the solution operator of PDE-based inverse problems without labeled training data.
  arXiv  Detail & Related papers  (2024-12-04T09:38:58Z)
• Quantitative Approximation for Neural Operators in Nonlinear Parabolic Equations [0.40964539027092917]
  We derive the approximation rate of solution operators for the nonlinear parabolic partial differential equations (PDEs) Our results show that neural operators can efficiently approximate these solution operators without the exponential growth in model complexity. A key insight in our proof is to transfer PDEs into the corresponding integral equations via Duahamel's principle, and to leverage the similarity between neural operators and Picard's iteration.
  arXiv  Detail & Related papers  (2024-10-03T02:28:17Z)
• Solving High-Dimensional PDEs with Latent Spectral Models [74.1011309005488]
  We present Latent Spectral Models (LSM) toward an efficient and precise solver for high-dimensional PDEs. Inspired by classical spectral methods in numerical analysis, we design a neural spectral block to solve PDEs in the latent space. LSM achieves consistent state-of-the-art and yields a relative gain of 11.5% averaged on seven benchmarks.
  arXiv  Detail & Related papers  (2023-01-30T04:58:40Z)
• Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities [5.735035463793008]
  A large class of hyperbolic and advection-dominated PDEs can have solutions with discontinuities. We rigorously prove, in terms of lower approximation bounds, that methods which entail a linear reconstruction step fail to efficiently approximate the solution operator of such PDEs. We show that certain methods employing a non-linear reconstruction mechanism can overcome these fundamental lower bounds and approximate the underlying operator efficiently.
  arXiv  Detail & Related papers  (2022-10-03T16:47:56Z)
• Physics-Informed Neural Operator for Learning Partial Differential Equations [55.406540167010014]
  PINO is the first hybrid approach incorporating data and PDE constraints at different resolutions to learn the operator. The resulting PINO model can accurately approximate the ground-truth solution operator for many popular PDE families.
  arXiv  Detail & Related papers  (2021-11-06T03:41:34Z)
• Solving PDEs on Unknown Manifolds with Machine Learning [8.220217498103315]
  This paper presents a mesh-free computational framework and machine learning theory for solving elliptic PDEs on unknown manifold. We show that the proposed NN solver can robustly generalize the PDE on new data points with errors that are almost identical to generalizations on new data points.
  arXiv  Detail & Related papers  (2021-06-12T03:55:15Z)
• Fourier Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  We formulate a new neural operator by parameterizing the integral kernel directly in Fourier space. We perform experiments on Burgers' equation, Darcy flow, and Navier-Stokes equation. It is up to three orders of magnitude faster compared to traditional PDE solvers.
  arXiv  Detail & Related papers  (2020-10-18T00:34:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.