Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces

• URL: http://arxiv.org/abs/2606.17419v1
• Date: Tue, 16 Jun 2026 02:00:59 GMT
• Title: Generalization Guarantees for Multi-Input Neural Operator Learning in Sobolev Spaces
• Abstract summary: We develop approximation and generalization error estimates for multi-input neural operators, with the output error measured in Sobolev norms.<n>In particular, in the balanced regime, the approximation and generalization rates are governed by the interaction between the input dimensions, regularities, and Sobolev orders.
• Score: 15.712274378790424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We develop approximation and generalization error estimates for multi-input neural operators, with the output error measured in Sobolev norms. In contrast to standard operator-learning settings with a single input function, our framework allows multiple input functions defined on possibly different domains, with different dimensions and Sobolev regularities. The derived rates explicitly quantify the contribution of each input space to the final error bound. In particular, in the balanced regime, the approximation and generalization rates are governed by the interaction between the input dimensions, regularities, and Sobolev orders, while the dependence on the model complexity retains a \(\log\log/\log\)-type structure. Our analysis provides a general theoretical framework for multi-input operator learning, including Sobolev training, and is applicable to operator learning problems arising from partial differential equations and scientific computing.

Related papers

• Kernel Methods for Learning Operators with Multiple Inputs and Outputs [0.5249805590164902]
  We introduce a kernel-based encoder-decoder framework for operator learning that separates observation, representation, learning, and reconstruction.<n>We develop this framework for multi-input, multi-output operator learning, where operators map between products of potentially distinct function spaces.<n>We specialize the approach to multiple operator learning by introducing KernelMO, a family of kernel methods with complementary operator-valued and product-space formulations.
  arXiv  Detail & Related papers  (2026-08-12T09:15:20Z)
• Error bounds for splitting methods in unitary problems [45.88028371034407]
  We present a systematic analysis of both local and global errors arising from arbitrary splitting methods applied to unitary problems.<n>The first is expressed in terms of operator norms, while the second is formulated using norms of commutators and can, under suitable assumptions, be extended to certain classes of operators.
  arXiv  Detail & Related papers  (2026-04-01T15:33:05Z)
• A Physics-informed Multi-resolution Neural Operator [1.4174475093445233]
  We introduce a physics-informed operator learning approach by extending the Resolution Independent Neural Operator (RINO) framework to a fully data-free setup.<n>In this study, we introduce a physics-informed operator learning approach by extending the Resolution Independent Neural Operator (RINO) framework to a fully data-free setup.
  arXiv  Detail & Related papers  (2025-10-27T19:50:02Z)
• RONOM: Reduced-Order Neural Operator Modeling [1.2016264781280588]
  This work introduces the reduced-order neural operator modeling (RONOM) framework, which bridges concepts from ROM and operator learning.<n>We establish a discretization error bound analogous to those in ROM, and get insights into RONOM's discretization convergence and discretization robustness.
  arXiv  Detail & Related papers  (2025-07-17T06:14:19Z)
• Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs [93.82811501035569]
  We introduce a new data efficient and highly parallelizable operator learning approach with reduced memory requirement and better generalization. MG-TFNO scales to large resolutions by leveraging local and global structures of full-scale, real-world phenomena. We demonstrate superior performance on the turbulent Navier-Stokes equations where we achieve less than half the error with over 150x compression.
  arXiv  Detail & Related papers  (2023-09-29T20:18:52Z)
• 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)
• Transformer for Partial Differential Equations' Operator Learning [0.0]
  We present an attention-based framework for data-driven operator learning, which we term Operator Transformer (OFormer) Our framework is built upon self-attention, cross-attention, and a set of point-wise multilayer perceptrons (MLPs)
  arXiv  Detail & Related papers  (2022-05-26T23:17:53Z)
• A Functional Perspective on Learning Symmetric Functions with Neural Networks [48.80300074254758]
  We study the learning and representation of neural networks defined on measures. We establish approximation and generalization bounds under different choices of regularization. The resulting models can be learned efficiently and enjoy generalization guarantees that extend across input sizes.
  arXiv  Detail & Related papers  (2020-08-16T16:34:33Z)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)
• Total Deep Variation: A Stable Regularizer for Inverse Problems [71.90933869570914]
  We introduce the data-driven general-purpose total deep variation regularizer. In its core, a convolutional neural network extracts local features on multiple scales and in successive blocks. We achieve state-of-the-art results for numerous imaging tasks.
  arXiv  Detail & Related papers  (2020-06-15T21:54:15Z)

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.