mlsanityData to 7 Oct 2026

DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators

arXiv 1910.03193 ↗First posted 8 Oct 2019cs.LG stat.MLcited by 1,965

Not on the map. Why?

Cited by 65 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

While it is widely known that neural networks are universal approximators of continuous functions, a less known and perhaps more powerful result is that a neural network with a single hidden layer can approximate accurately any nonlinear continuous operator. This universal approximation theorem is suggestive of the potential application of neural networks in learning nonlinear operators from data. However, the theorem guarantees only a small approximation error for a sufficient large network, and does not consider the important optimization and generalization errors. To realize this theorem in practice, we propose deep operator networks (DeepONets) to learn operators accurately and efficiently from a relatively small dataset. A DeepONet consists of two sub-networks, one for encoding the input function at a fixed number of sensors xi, i=1,dots,m (branch net), and another for encoding the locations for the output functions (trunk net). We perform systematic simulations for identifying two types of operators, i.e., dynamic systems and partial differential equations, and demonstrate that DeepONet significantly reduces the generalization error compared to the fully-connected networks. We also derive theoretically the dependence of the approximation error in terms of the number of sensors (where the input function is defined) as well as the input function type, and we verify the theorem with computational results. More importantly, we observe high-order error convergence in our computational tests, namely polynomial rates (from half order to fourth order) and even exponential convergence with respect to the training dataset size.

Key facts. Cited by 1,965 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 66; 2022: 148; 2023: 273; 2024: 351; 2025: 491; 2026: 636.

1,965 papers.

Sort:

By area:

  1. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  2. 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 603
  3. 2021Learning the solution operator of parametric partial differential equations with physics-informed DeepOnetscited by 537
  4. 2021Neural Operator: Learning Maps Between Function Spacescited by 413
  5. 2021Choose a Transformer: Fourier or Galerkincited by 333
  6. 2023ClimaX: A foundation model for weather and climatecited by 325
  7. 2024Transolver: A Fast Transformer Solver for PDEs on General Geometriescited by 299
  8. 2022Transformer for Partial Differential Equations' Operator Learningcited by 270
  9. 2021Modern Koopman Theory for Dynamical Systemscited by 269
  10. 2021Multiwavelet-based Operator Learning for Differential Equationscited by 229
  11. 2023Neural Operators for Accelerating Scientific Simulations and Designcited by 218
  12. 2023Convolutional Neural Operators for robust and accurate learning of PDEscited by 207
38 more
  1. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 205
  2. 2022Towards Multi-spatiotemporal-scale Generalized PDE Modelingcited by 190
  3. 2022MIONet: Learning multiple-input operators via tensor productcited by 180
  4. 2022Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisonscited by 169
  5. 2021Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equationscited by 142
  6. 2024DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Trainingcited by 137
  7. 2023Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behaviorcited by 128
  8. 2022Physics-Informed Deep Neural Operator Networkscited by 110
  9. 2024Challenges in Training PINNs: A Loss Landscape Perspectivecited by 109
  10. 2024A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networkscited by 103
  11. 2024DiffusionPDE: Generative PDE-Solving Under Partial Observationcited by 100
  12. 2021A physics-informed variational DeepONet for predicting the crack path in brittle materialscited by 98
  13. 2023In-Context Operator Learning with Data Prompts for Differential Equation Problemscited by 98
  14. 2021PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEscited by 97
  15. 2022Multifidelity deep neural operators for efficient learning of partial differential equations with application to fast inverse design of nanoscale heat transportcited by 92
  16. 2022Clifford Neural Layers for PDE Modelingcited by 91
  17. 2022Physics-Informed Machine Learning: A Survey on Problems, Methods and Applicationscited by 88
  18. 2021Long-time integration of parametric evolution equations with physics-informed DeepONetscited by 87
  19. 2024Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equationscited by 87
  20. 2021Improved architectures and training algorithms for deep operator networkscited by 85
  21. 2023Solving High-Dimensional PDEs with Latent Spectral Modelscited by 84
  22. 2024Operator Learning: Algorithms and Analysiscited by 84
  23. 2022Deep transfer operator learning for partial differential equations under conditional shiftcited by 83
  24. 2022NOMAD: Nonlinear Manifold Decoders for Operator Learningcited by 81
  25. 2023Tackling the Curse of Dimensionality with Physics-Informed Neural Networkscited by 78
  26. 2024ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEscited by 78
  27. 2022AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutionscited by 77
  28. 2023A Mathematical Guide to Operator Learningcited by 74
  29. 2022Learning two-phase microstructure evolution using neural operators and autoencoder architecturescited by 72
  30. 2022Continuous PDE Dynamics Forecasting with Implicit Neural Representationscited by 71
  31. 2024PirateNets: Physics-informed Deep Learning with Residual Adaptive Networkscited by 70
  32. 2022Overview frequency principle/spectral bias in deep learningcited by 68
  33. 2023Can Physics-Informed Neural Networks beat the Finite Element Method?cited by 68
  34. 2021Closed-form Continuous-time Neural Modelscited by 65
  35. 2022Learning Deep Implicit Fourier Neural Operators (IFNOs) with Applications to Heterogeneous Material Modelingcited by 65
  36. 2022Generic bounds on the approximation error for physics-informed (and) operator learningcited by 65
  37. 2024Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networkscited by 64
  38. 2022Reliable extrapolation of deep neural operators informed by physics or sparse observationscited by 62

50 most cited of 1,965 All 1,965 (JSON)