Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation

• URL: http://arxiv.org/abs/2605.12997v1
• Date: Wed, 13 May 2026 04:53:36 GMT
• Title: Frequency Bias and OOD Generalization in Neural Operators under a Variable-Coefficient Wave Equation
• Abstract summary: We study operator learning in a wave propagation setting governed by a one-dimensional variable-coefficient wave equation.<n>Under smoothness shifts, both models maintain stable performance, with FNO achieving lower error.<n>Under frequency shifts, FNO exhibits a sharp increase in error under unseen high-frequency inputs, whereas DeepONet shows milder degradation despite higher overall error.
• Score: 3.918109426744543
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Neural operators learn to map initial conditions to the terminal solution of partial differential equations (PDEs), providing a surrogate for the full operator mapping. This enables rapid prediction across different input configurations. While recent neural operator architectures have demonstrated strong performance on diverse PDE tasks, their behavior under structured distribution shifts remains insufficiently understood. To investigate this, we study operator learning in a wave propagation setting governed by a one-dimensional variable-coefficient wave equation, using two representative architectures, the Fourier Neural Operator (FNO) and the Deep Operator Network (DeepONet). To examine their generalization under distribution shifts, we consider structured out-of-distribution (OOD) settings that independently vary input frequency and coefficient smoothness. The results show that under smoothness shifts, both models maintain stable performance, with FNO achieving lower error. In contrast, under frequency shifts, FNO exhibits a sharp increase in error under unseen high-frequency inputs, whereas DeepONet shows milder degradation despite higher overall error. Our analysis reveals that these differences arise from how each architecture represents and responds to variations in frequency structure. Together, these findings highlight a fundamental gap between strong in-distribution performance and generalization under distribution shifts in operator learning, underscoring the role of architectural representation bias in developing more reliable neural operators for physics-based PDE simulations beyond the training distribution.

Related papers

• Learning Metamaterial Eigenmodes with Wavelet-Encoded Fourier Neural Operators [57.64362886310329]
  We show that a machine learning surrogate based on neural operators can learn and predict multiple eigenmodes of the elastic wave equation.<n>For metamaterial design, the resulting surrogate accelerates the simulation stage of the design cycle by three orders of magnitude relative to finite element analysis on a consumer-grade CPU.<n>These results also carry broader implications for designing input encodings in other multi-mode PDE solvers based on spectral neural operators.
  arXiv  Detail & Related papers  (2026-09-08T01:21:46Z)
• Sensitivity-Constrained Neural Operators for Data-Efficient Forward and Inverse Modeling of Partial Differential Equation Systems [7.72071408793585]
  We study sensitivity-constrained neural operators (SC-NOs)<n>SC-NOs augment standard training with solver-derived Jacobian supervision.<n>We evaluate SC-NOs on advection--diffusion and RANS--Spalart--Allmaras benchmarks, input-dimensionality scaling tests, long-horizon autoregressive rollout, and a shallow-water Tohoku tsunami source-inversion case.
  arXiv  Detail & Related papers  (2026-08-30T16:37:25Z)
• Inertial Manifold Neural Operator for Dissipative Time-Dependent Partial Differential Equations [0.5586191108738563]
  In this paper, we introduce the Inertial Manifold Neural Operator (IMNO) for solving dissipative time-dependent partial differential equations (PDEs)<n>Unlike standard neural operator architectures such as the Fourier Neural Operator (FNO), IMNO explicitly leverages the low-dimensional structure to achieve better physical interpretability, accuracy, and stability.<n>For shift-equivariant PDEs, we introduce a shift-equivariant variant (IMNO-SE) of the proposed neural operator, ensuring that a spatial shift in the input induces the same spatial shift in the output.
  arXiv  Detail & Related papers  (2026-08-24T17:49:30Z)
• Late Fusion Neural Operators for Extrapolation Across Parameter Space in Partial Differential Equations [3.4369924555307794]
  We introduce the Late Fusion Neural Operator, an architecture that disentangles learning state dynamics from parameter effects.<n>Our approach combines neural operators for learning latent state representations with sparse regression to incorporate parameter information in a structured manner.
  arXiv  Detail & Related papers  (2026-04-17T21:52:37Z)
• HFNO: an interpretable data-driven decomposition strategy for turbulent flows [0.0]
  We present a novel FNO-based architecture tailored for reduced-order modeling of turbulent fluid flows.<n>The proposed architecture processes wavenumber bins in parallel, enabling approximation of dispersion relations and non-linear interactions.<n>We evaluate the proposed model on a series of increasingly complex dynamical systems.
  arXiv  Detail & Related papers  (2025-11-03T12:57:19Z)
• LOGLO-FNO: Efficient Learning of Local and Global Features in Fourier Neural Operators [20.77877474840923]
  High-frequency information is a critical challenge in machine learning.<n>Deep neural nets exhibit the so-called spectral bias toward learning low-frequency components.<n>We propose a novel frequency-sensitive loss term based on radially binned spectral errors.
  arXiv  Detail & Related papers  (2025-04-05T19:35:04Z)
• Component Fourier Neural Operator for Singularly Perturbed Differential Equations [3.9482103923304877]
  Solving Singularly Perturbed Differential Equations (SPDEs) poses computational challenges arising from the rapid transitions in their solutions within thin regions. In this manuscript, we introduce Component Fourier Neural Operator (ComFNO), an innovative operator learning method that builds upon Fourier Neural Operator (FNO) Our approach is not limited to FNO and can be applied to other neural network frameworks, such as Deep Operator Network (DeepONet)
  arXiv  Detail & Related papers  (2024-09-07T09:40:51Z)
• Neural Operators with Localized Integral and Differential Kernels [77.76991758980003]
  We present a principled approach to operator learning that can capture local features under two frameworks. We prove that we obtain differential operators under an appropriate scaling of the kernel values of CNNs. To obtain local integral operators, we utilize suitable basis representations for the kernels based on discrete-continuous convolutions.
  arXiv  Detail & Related papers  (2024-02-26T18:59:31Z)
• Enhancing Solutions for Complex PDEs: Introducing Complementary Convolution and Equivariant Attention in Fourier Neural Operators [17.91230192726962]
  We propose a novel hierarchical Fourier neural operator along with convolution-residual layers and attention mechanisms to solve complex PDEs. We find that the proposed method achieves superior performance in these PDE benchmarks, especially for equations characterized by rapid coefficient variations.
  arXiv  Detail & Related papers  (2023-11-21T11:04:13Z)
• Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs [86.35471039808023]
  We introduce the Incremental Fourier Neural Operator (iFNO), which progressively increases the number of frequency modes used by the model. We show that iFNO reduces total training time while maintaining or improving generalization performance across various datasets. Our method demonstrates a 10% lower testing error, using 20% fewer frequency modes compared to the existing Fourier Neural Operator, while also achieving a 30% faster training.
  arXiv  Detail & Related papers  (2022-11-28T09:57:15Z)
• Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations [64.78260098263489]
  In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs) We show that PINNs eventually fail to produce correct solutions to these benchmarks as their complexity increases. We identify several reasons why this may be the case, including insufficient network capacity, poor conditioning of the ODEs, and high local curvature, as measured by the Laplacian of the PINN loss.
  arXiv  Detail & Related papers  (2022-10-14T15:01:32Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Factorized Fourier Neural Operators [77.47313102926017]
  The Factorized Fourier Neural Operator (F-FNO) is a learning-based method for simulating partial differential equations. We show that our model maintains an error rate of 2% while still running an order of magnitude faster than a numerical solver.
  arXiv  Detail & Related papers  (2021-11-27T03:34:13Z)
• Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics [73.77459272878025]
  We propose to enhance the supervised signal in learning dynamics by pre-training a neural differential operator (NDO) NDO is pre-trained on a class of symbolic functions, and it learns the mapping between the trajectory samples of these functions to their derivatives. We provide theoretical guarantee on that the output of NDO can well approximate the ground truth derivatives by proper tuning the complexity of the library.
  arXiv  Detail & Related papers  (2021-06-08T08:04:47Z)

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.