pith. sign in

arxiv: 2605.22557 · v1 · pith:TILX2476new · submitted 2026-05-21 · 💻 cs.LG · cs.NA· math.NA

Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approcimations

Shuang Chen , Juncai He , Xue-Cheng Tai This is my paper

Pith reviewed 2026-05-22 07:24 UTC · model grok-4.3

classification 💻 cs.LG cs.NAmath.NA
keywords neural flowsuniversal approximationneural operatorsoperator learningcontinuous-depth modelsResNet architecturesinfinite-dimensional spacesconvolutional models
0
0 comments X

The pith

Neural flows can universally approximate any operator between infinite-dimensional function spaces.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces an abstract framework for neural flows that treats both neural networks and neural operators as continuous-depth dynamical systems. It establishes well-posedness for these flows and proves they can approximate arbitrary operators on finite- or infinite-dimensional spaces. A key result is the first universal approximation guarantee for flow-based models acting between infinite-dimensional spaces. The framework also covers convolutional variants and shows that standard discretizations recover both residual and plain network architectures. This matters because operator learning often involves function spaces rather than vectors, and a single continuous model that rigorously approximates any mapping in those spaces could simplify theory and design for tasks like solving partial differential equations.

Core claim

We introduce an abstract neural flow framework containing two continuous-depth models with composition and separation structures. These cover both finite-dimensional function approximation and infinite-dimensional operator approximation. We prove well-posedness and universal approximation properties for the neural flows, including the first such result for flow-based models between infinite-dimensional spaces. Universal approximation also holds for convolutional neural flow models. Suitable time discretizations recover ResNet-type architectures from the composition structure and plain architectures from the separation structure, yielding a unified flow-based route to both residual and plain,

What carries the argument

The abstract neural flow framework with composition and separation structures, which models networks and operators as continuous-time flows whose well-posedness and approximation properties are proved directly in the chosen function spaces.

If this is right

  • Flow-based models now have rigorous guarantees when learning mappings between function spaces rather than finite vectors.
  • Both residual and plain architectures for operators can be obtained from the same continuous flow by different discretizations.
  • Convolutional neural flows inherit universal approximation on suitable function spaces.
  • A single continuous-depth perspective unifies the analysis of many existing neural network and neural operator designs.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The framework may enable new training algorithms that integrate the continuous flow directly instead of discretizing first.
  • It suggests testing whether flow models can approximate solution operators for specific families of PDEs with provable rates.
  • Connections to dynamical systems could help analyze stability or generalization of operator learners in infinite dimensions.
  • Similar flow constructions might extend to other structures such as graph or manifold-valued operators.

Load-bearing premise

The neural flows must remain well-posed in the chosen Banach or Hilbert spaces and the activation functions must satisfy the conditions required by the universal approximation theorems.

What would settle it

An explicit continuous operator between two infinite-dimensional spaces for which the approximation error of any neural flow with the given structures stays bounded away from zero no matter how the flow parameters are chosen.

read the original abstract

We introduce an abstract neural flow framework for neural networks and neural operators. The framework contains two continuous-depth models, namely neural flows with composition and separation structures, and covers both finite-dimensional function approximation and infinite-dimensional operator approximation. We prove well-posedness and universal approximation properties for the corresponding neural flows, including, to the best of our knowledge, the first universal approximation result for flow-based models between infinite-dimensional spaces. We also obtain universal approximation results for convolutional neural flow models. Through suitable time discretizations, the composition structure recovers ResNet-type architectures, while the separation structure, via a splitting-based discretization, yields plain architectures. This gives a unified flow-based route to both residual and plain architectures for neural networks and neural operators with fully connected or convolutional linear layers.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces an abstract neural flow framework for neural networks and neural operators, featuring two continuous-depth models with composition and separation structures. It proves well-posedness and universal approximation properties for these flows in both finite- and infinite-dimensional settings, claiming the first universal approximation result for flow-based models between infinite-dimensional spaces. The work also derives results for convolutional neural flow models and shows that time discretizations recover ResNet-type architectures via the composition structure and plain architectures via splitting-based discretization of the separation structure.

Significance. If the derivations are complete and the function-space arguments rigorous, the framework would provide a unified flow-based perspective linking residual and feedforward architectures for both networks and operators, with the infinite-dimensional universal approximation result representing a notable theoretical advance in operator learning.

major comments (2)
  1. [Section 3] The well-posedness claim for the neural flow ODE in infinite-dimensional Banach or Hilbert spaces (central to applying the universal approximation theorem) requires explicit verification that the neural vector field satisfies global Lipschitz or linear growth conditions; without this, global existence and uniqueness may fail for arbitrary time horizons and target operators.
  2. [Section 5] Theorem on universal approximation for infinite-dimensional operators (likely in §5) assumes the flow map is continuous in the chosen topology, but the separation structure may only guarantee this under additional regularity on the activation functions or network widths that are not fully stated.
minor comments (2)
  1. [Abstract] The abstract contains a typographical error: 'Approcimations' should read 'Approximations'.
  2. [Section 2] Notation for the composition and separation structures should be introduced with explicit definitions of the associated operators before the well-posedness statements.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their careful reading of the manuscript and for the constructive comments on the well-posedness and continuity aspects of the neural flow framework. We address each major comment below and will incorporate clarifications and additional details into the revised version.

read point-by-point responses

  1. Referee: [Section 3] The well-posedness claim for the neural flow ODE in infinite-dimensional Banach or Hilbert spaces (central to applying the universal approximation theorem) requires explicit verification that the neural vector field satisfies global Lipschitz or linear growth conditions; without this, global existence and uniqueness may fail for arbitrary time horizons and target operators.

    Authors: We agree that an explicit verification strengthens the rigor of the infinite-dimensional case. In Section 3 the neural vector field is defined via a neural operator with bounded linear layers and globally Lipschitz activations (ReLU or tanh). Under the standing assumption that the network parameters remain bounded in the appropriate operator norm, the vector field satisfies a global Lipschitz condition whose constant depends on the time horizon T but is finite for any fixed T. We will add a short lemma (or remark) immediately after the well-posedness statement that derives the linear-growth bound directly from the finite-dimensional parameter space and the continuous embedding of the parameter space into the space of bounded operators on the Banach space. This guarantees global existence and uniqueness on any finite time interval without further restrictions on the target operator. revision: yes

  2. Referee: [Section 5] Theorem on universal approximation for infinite-dimensional operators (likely in §5) assumes the flow map is continuous in the chosen topology, but the separation structure may only guarantee this under additional regularity on the activation functions or network widths that are not fully stated.

    Authors: We thank the referee for highlighting this point. The separation-structure flow is constructed via a splitting scheme whose convergence to the continuous flow relies on the vector field being uniformly Lipschitz in the operator norm. We already assume globally Lipschitz activations, but the dependence of the Lipschitz constant on network width is not stated explicitly. In the revised manuscript we will add a sentence to the statement of the infinite-dimensional universal-approximation theorem (and to the corresponding proof sketch) requiring that the family of networks be chosen so that the operator-norm Lipschitz constants remain uniformly bounded with respect to width. This is a mild and standard restriction that is satisfied by the concrete convolutional and fully-connected constructions used later in the paper; we will also note that the result continues to hold for any activation satisfying a uniform Lipschitz bound. revision: partial

Circularity Check

0 steps flagged

No significant circularity detected in theoretical derivation

full rationale

The paper introduces an abstract framework for neural flows with composition and separation structures, then claims to prove well-posedness and universal approximation results for both finite-dimensional networks and infinite-dimensional operators. These are presented as mathematical theorems under stated assumptions on Banach/Hilbert spaces and activation functions. No quoted step reduces a prediction or central result to a fitted parameter, self-definition, or load-bearing self-citation chain; the derivation chain relies on standard functional analysis techniques rather than renaming or smuggling in prior results by the same authors as unverified axioms. The work is self-contained against external benchmarks for the claimed proofs.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The central claims rest on standard assumptions about function spaces and activation functions plus the newly introduced neural flow structures; no free parameters are fitted to data.

axioms (2)
  • domain assumption The underlying spaces are suitable topological vector spaces (e.g., Banach spaces) in which the operators are continuous.
    Required for well-posedness and approximation statements in infinite dimensions.
  • standard math Activation functions possess universal approximation properties or sufficient regularity (continuity, Lipschitz) in the finite-dimensional case.
    Standard background assumption for neural network approximation theorems.
invented entities (1)
  • Neural flow operators with composition and separation structures no independent evidence
    purpose: To provide continuous-depth models that unify finite- and infinite-dimensional approximation and recover discrete architectures via discretization.
    New framework introduced by the paper; no independent external evidence supplied in the abstract.

pith-pipeline@v0.9.0 · 5664 in / 1552 out tokens · 60067 ms · 2026-05-22T07:24:37.976553+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

165 extracted references · 165 canonical work pages · 5 internal anchors

  1. [1]

    Control and machine learning , volume =

    Zuazua, Enrique , date-added =. Control and machine learning , volume =. Collections , note =

    work page

  2. [2]

    A Regularized Convolutional Neural Network for Semantic Image Segmentation

    Jia, Fan and Liu, Jun and Tai, Xue Cheng , doi =. Analysis and Applications , keywords =. 1907.05287 , file =

    work page internal anchor Pith review Pith/arXiv arXiv 1907

  3. [3]

    Self equivalence of the alternating direction method of multipliers,

    Glowinski, Roland and Pan, Tsorng-whay and Tai, Xue-cheng , booktitle =. doi:10.1007/978-3-319-41589-5 , editor =

    work page doi:10.1007/978-3-319-41589-5

  4. [4]

    IEEE Transactions on Information Theory , volume=

    Universal approximation bounds for superpositions of a sigmoidal function , author=. IEEE Transactions on Information Theory , volume=. 1993 , publisher=

    work page 1993

  5. [5]

    Mathematics of Control, Signals and Systems , volume=

    Approximation by superpositions of a sigmoidal function , author=. Mathematics of Control, Signals and Systems , volume=. 1989 , publisher=

    work page 1989

  6. [6]

    Neural Networks , volume=

    Multilayer feedforward networks are universal approximators , author=. Neural Networks , volume=. 1989 , publisher=

    work page 1989

  7. [7]

    Neural Networks , volume=

    Error bounds for approximations with deep ReLU networks , author=. Neural Networks , volume=. 2017 , publisher=

    work page 2017

  8. [8]

    Proceedings of the 29th Annual Conference on Learning Theory , pages=

    Benefits of depth in neural networks , author=. Proceedings of the 29th Annual Conference on Learning Theory , pages=. 2016 , publisher=

    work page 2016

  9. [9]

    Applied and Computational Harmonic Analysis , volume=

    Universality of deep convolutional neural networks , author=. Applied and Computational Harmonic Analysis , volume=. 2020 , publisher=

    work page 2020

  10. [10]

    Journal of Machine Learning Research , volume=

    On universal approximation and error bounds for Fourier neural operators , author=. Journal of Machine Learning Research , volume=

    work page

  11. [11]

    Journal of Machine Learning Research , volume=

    Neural operator: Learning maps between function spaces with applications to PDEs , author=. Journal of Machine Learning Research , volume=

    work page

  12. [12]

    Advances in Neural Information Processing Systems , volume=

    Neural ordinary differential equations , author=. Advances in Neural Information Processing Systems , volume=

    work page

  13. [13]

    Juncai He and Xinliang Liu and Jinchao Xu , booktitle=. Mg. 2024 , url=

    work page 2024

  14. [14]

    Mathematical Foundations of Computing , volume=

    A mathematical explanation of UNet , author=. Mathematical Foundations of Computing , volume=. 2025 , publisher=

    work page 2025

  15. [15]

    International Conference on Machine Learning , pages=

    On enhancing expressive power via compositions of single 763 fixed-size relu network , author=. International Conference on Machine Learning , pages=

    work page

  16. [16]

    2022 , issn =

    Optimal approximation rate of ReLU networks in terms of width and depth , journal =. 2022 , issn =. doi:https://doi.org/10.1016/j.matpur.2021.07.009 , url =

    work page doi:10.1016/j.matpur.2021.07.009 2022

  17. [17]

    2025 , issn =

    Universal approximation property of ODENet and ResNet with a single activation function , journal =. 2025 , issn =

    work page 2025

  18. [18]

    , journal =

    Deep learning via dynamical systems: An approximation perspective. , journal =. 2023 , doi =

    work page 2023

  19. [19]

    2020 , doi =

    RELU DEEP NEURAL NETWORKS AND LINEAR FINITE ELEMENTS , journal =. 2020 , doi =

    work page 2020

  20. [20]

    2025 , doi =

    Achieving Universal Approximation and Universal Interpolation via Nonlinearity of Control Families , journal =. 2025 , doi =

    work page 2025

  21. [21]

    A Minimal Control Family of Dynamical Systems for Universal Approximation , year=

    Duan, Yifei and Cai, Yongqiang , journal=. A Minimal Control Family of Dynamical Systems for Universal Approximation , year=

    work page

  22. [22]

    SIAM Journal on Imaging Sciences , volume=

    PottsMGNet: A mathematical explanation of encoder-decoder based neural networks , author=. SIAM Journal on Imaging Sciences , volume=. 2024 , publisher=

    work page 2024

  23. [23]

    arXiv preprint arXiv:2209.11395 , year=

    Achieve the minimum width of neural networks for universal approximation , author=. arXiv preprint arXiv:2209.11395 , year=

    work page arXiv

  24. [24]

    Advances in neural information processing systems , volume=

    Resnet with one-neuron hidden layers is a universal approximator , author=. Advances in neural information processing systems , volume=

    work page

  25. [25]

    Forty-first International Conference on Machine Learning , year=

    Characterizing ResNet's Universal Approximation Capability , author=. Forty-first International Conference on Machine Learning , year=

    work page

  26. [29]

    SIAM Journal on Mathematics of Data Science , volume=

    Deep Neural Networks, Generic Universal Interpolation, and Controlled ODEs , author=. SIAM Journal on Mathematics of Data Science , volume=. 2020 , doi=

    work page 2020

  27. [30]

    Advances in Neural Information Processing Systems , volume=

    Neural Ordinary Differential Equations , author=. Advances in Neural Information Processing Systems , volume=. 2018 , url=

    work page 2018

  28. [31]

    Journal of Machine Learning Research , volume=

    Deep Neural Network Approximation of Invariant Functions through Dynamical Systems , author=. Journal of Machine Learning Research , volume=. 2024 , url=

    work page 2024

  29. [32]

    SIAM Journal on Control and Optimization , volume=

    Interpolation, Approximation, and Controllability of Deep Neural Networks , author=. SIAM Journal on Control and Optimization , volume=. 2025 , doi=

    work page 2025

  30. [33]

    2020 , eprint=

    Neural Operator: Graph Kernel Network for Partial Differential Equations , author=. 2020 , eprint=

    work page 2020

  31. [34]

    Proceedings of the American Mathematical Society , volume=

    Equivalence of approximation by convolutional neural networks and fully-connected networks , author=. Proceedings of the American Mathematical Society , volume=

    work page

  32. [35]

    Approximation and non-parametric estimation of

    Oono, Kenta and Suzuki, Taiji , booktitle=. Approximation and non-parametric estimation of. 2019 , organization=

    work page 2019

  33. [36]

    nature , volume=

    Deep learning , author=. nature , volume=. 2015 , publisher=

    work page 2015

  34. [37]

    Proceedings of the IEEE , volume=

    Gradient-based learning applied to document recognition , author=. Proceedings of the IEEE , volume=

    work page

  35. [38]

    Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

    Deep residual learning for image recognition , author=. Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

    work page

  36. [39]

    Advances in neural information processing systems , volume=

    Imagenet classification with deep convolutional neural networks , author=. Advances in neural information processing systems , volume=

    work page

  37. [40]

    2017 , publisher=

    Deep Learning , author=. 2017 , publisher=

    work page 2017

  38. [41]

    Nature machine intelligence , volume=

    Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators , author=. Nature machine intelligence , volume=. 2021 , publisher=

    work page 2021

  39. [42]

    International Conference on Learning Representations , year=

    Fourier Neural Operator for Parametric Partial Differential Equations , author=. International Conference on Learning Representations , year=

    work page

  40. [43]

    IEEE Transactions on Information Theory , volume=

    Approximation by combinations of ReLU and squared ReLU ridge functions with ^1 and ^0 controls , author=. IEEE Transactions on Information Theory , volume=. 2018 , publisher=

    work page 2018

  41. [44]

    Neural networks , volume=

    Multilayer feedforward networks with a nonpolynomial activation function can approximate any function , author=. Neural networks , volume=. 1993 , publisher=

    work page 1993

  42. [45]

    Advances in Computational Mathematics , volume=

    Approximation properties of a multilayered feedforward artificial neural network , author=. Advances in Computational Mathematics , volume=. 1993 , publisher=

    work page 1993

  43. [46]

    Advances in applied mathematics , volume=

    Degree of approximation by neural and translation networks with a single hidden layer , author=. Advances in applied mathematics , volume=. 1995 , publisher=

    work page 1995

  44. [48]

    Communications in Mathematical Sciences , volume=

    A priori estimates of the population risk for two-layer neural networks , author=. Communications in Mathematical Sciences , volume=. 2019 , publisher=

    work page 2019

  45. [49]

    Foundations of Computational Mathematics , volume=

    Sharp bounds on the approximation rates, metric entropy, and n-widths of shallow neural networks , author=. Foundations of Computational Mathematics , volume=. 2024 , publisher=

    work page 2024

  46. [51]

    Journal of Machine Learning Research , year =

    Francis Bach , title =. Journal of Machine Learning Research , year =

    work page

  47. [54]

    Advances in neural information processing systems , volume=

    Almost linear VC dimension bounds for piecewise polynomial networks , author=. Advances in neural information processing systems , volume=

    work page

  48. [55]

    The Journal of Machine Learning Research , volume=

    Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networks , author=. The Journal of Machine Learning Research , volume=. 2019 , publisher=

    work page 2019

  49. [57]

    Optimal approximation rate of

    Shen, Zuowei and Yang, Haizhao and Zhang, Shijun , journal=. Optimal approximation rate of. 2022 , publisher=

    work page 2022

  50. [58]

    Advances in Neural Information Processing Systems , volume=

    Nearly optimal VC-dimension and pseudo-dimension bounds for deep neural network derivatives , author=. Advances in Neural Information Processing Systems , volume=

    work page

  51. [59]

    East Asian Journal on Applied Mathematics , volume=

    Approximation analysis of convolutional neural networks , author=. East Asian Journal on Applied Mathematics , volume=

    work page

  52. [60]

    Research in the mathematical sciences , volume=

    Approximation properties of deep ReLU CNNs , author=. Research in the mathematical sciences , volume=. 2022 , publisher=

    work page 2022

  53. [61]

    Analysis and Applications , volume=

    Approximation analysis of CNNs from a feature extraction view , author=. Analysis and Applications , volume=. 2024 , publisher=

    work page 2024

  54. [63]

    International Conference on Machine Learning , pages=

    Minimum width of leaky-ReLU neural networks for uniform universal approximation , author=. International Conference on Machine Learning , pages=. 2023 , organization=

    work page 2023

  55. [64]

    The Eleventh International Conference on Learning Representations , year=

    Achieve the Minimum Width of Neural Networks for Universal Approximation , author=. The Eleventh International Conference on Learning Representations , year=

    work page

  56. [65]

    International Conference on Learning Representations , year=

    Multi-level Residual Networks from Dynamical Systems View , author=. International Conference on Learning Representations , year=

    work page

  57. [66]

    Communications in Mathematics and Statistics , volume=

    A Proposal on Machine Learning via Dynamical Systems , author=. Communications in Mathematics and Statistics , volume=. 2017 , publisher=

    work page 2017

  58. [67]

    Proceedings of the AAAI conference on artificial intelligence , volume=

    Learning across scales---multiscale methods for convolution neural networks , author=. Proceedings of the AAAI conference on artificial intelligence , volume=

    work page

  59. [69]

    International conference on machine learning , pages=

    Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations , author=. International conference on machine learning , pages=. 2018 , organization=

    work page 2018

  60. [70]

    Journal of Computational Physics , volume=

    Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models , author=. Journal of Computational Physics , volume=. 2022 , publisher=

    work page 2022

  61. [71]

    Mathematical Models and Methods in Applied Sciences , year=

    Deep neural ode operator networks for pdes , author=. Mathematical Models and Methods in Applied Sciences , year=

    work page

  62. [72]

    The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=

    Mean Flows for One-step Generative Modeling , author=. The Thirty-ninth Annual Conference on Neural Information Processing Systems , year=

    work page

  63. [73]

    The Eleventh International Conference on Learning Representations , year=

    Flow Matching for Generative Modeling , author=. The Eleventh International Conference on Learning Representations , year=

    work page

  64. [76]

    Journal of Computational Mathematics , volume=

    ReLU deep neural networks and linear finite elements , author=. Journal of Computational Mathematics , volume=. 2020 , publisher=

    work page 2020

  65. [78]

    Advances in neural information processing systems , volume=

    On the number of linear regions of deep neural networks , author=. Advances in neural information processing systems , volume=

    work page

  66. [79]

    Advances in neural information processing systems , volume=

    The expressive power of neural networks: A view from the width , author=. Advances in neural information processing systems , volume=

    work page

  67. [80]

    shallow networks: An approximation theory perspective , author=

    Deep vs. shallow networks: An approximation theory perspective , author=. Analysis and Applications , volume=. 2016 , publisher=

    work page 2016

  68. [81]

    Computers & Mathematics with Applications , volume=

    ReLU deep neural networks from the hierarchical basis perspective , author=. Computers & Mathematics with Applications , volume=. 2022 , publisher=

    work page 2022

  69. [82]

    Analysis and Applications , volume=

    Deep ReLU networks and high-order finite element methods , author=. Analysis and Applications , volume=. 2020 , publisher=

    work page 2020

  70. [83]

    Journal of Machine Learning Research , volume=

    Optimal approximation rates for deep ReLU neural networks on Sobolev and Besov spaces , author=. Journal of Machine Learning Research , volume=

    work page

  71. [84]

    Transactions of Mathematics and its Applications , volume=

    Error estimates for deeponets: A deep learning framework in infinite dimensions , author=. Transactions of Mathematics and its Applications , volume=. 2022 , publisher=

    work page 2022

  72. [86]

    SIAM/ASA Journal on Uncertainty Quantification , volume=

    Adaptive operator learning for infinite-dimensional Bayesian inverse problems , author=. SIAM/ASA Journal on Uncertainty Quantification , volume=. 2024 , publisher=

    work page 2024

  73. [87]

    Advances in neural information processing systems , volume=

    Choose a transformer: Fourier or galerkin , author=. Advances in neural information processing systems , volume=

    work page

  74. [88]

    ICLR 2023 workshop on physics for machine learning , year=

    Convolutional neural operators , author=. ICLR 2023 workshop on physics for machine learning , year=

    work page 2023

  75. [89]

    Journal of Computational Physics , volume=

    Mitigating spectral bias for the multiscale operator learning , author=. Journal of Computational Physics , volume=. 2024 , publisher=

    work page 2024

  76. [90]

    International Conference on Machine Learning , pages=

    Transolver: A Fast Transformer Solver for PDEs on General Geometries , author=. International Conference on Machine Learning , pages=. 2024 , organization=

    work page 2024

  77. [91]

    IEEE Transactions on Neural Networks , volume=

    Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems , author=. IEEE Transactions on Neural Networks , volume=. 1995 , publisher=

    work page 1995

  78. [92]

    Proceedings of the 40th International Conference on Machine Learning , series=

    Neural Inverse Operators for Solving PDE Inverse Problems , author=. Proceedings of the 40th International Conference on Machine Learning , series=. 2023 , publisher=

    work page 2023

  79. [93]

    1970 , publisher=

    Convex Analysis , author=. 1970 , publisher=

    work page 1970

  80. [94]

    2017 , publisher=

    Convex Analysis and Monotone Operator Theory in Hilbert Spaces , author=. 2017 , publisher=

    work page 2017

Showing first 80 references.