betaFeedback

WorksMathematics

Neural Operator Surrogates for Landweber Iteration in Solving Inverse Problems

Abstract

Neural operators can accurately approximate well-posed mappings, but for unbounded or discontinuous operators, common in inverse problems, we verify that their network parameters often blow up in architectures such as DeepONet and FNO. To solve inverse problems stably, we use Landweber iteration, which requires only a forward map and the adjoint of its derivative (linearisation). To reduce repeated PDE forward evaluations, we replace the forward operator and its derivative with a differentiable neural-operator surrogate. We show that encoder-network-decoder operators, including generalised DeepONets and fully coupled Fourier operators, approximate both the forward map and its derivative. A modified discrepancy principle ensures decreasing error before finite stopping. With a compact preconditioner, the iterates remain in a compact set where accurate surrogates exist, and the stopped reconstructions converge as data and surrogate errors vanish under a regularity condition. We also relate the theory to derivative-informed training along finite directions, showing that the preconditioner determines which derivative errors affect the Landweber iteration update. Experiments on identifying a reaction coefficient in an elliptic equation show that smoothing reduces late-iteration deterioration for less accurate surrogates but slows sharp-feature recovery, and that smaller derivative errors along training directions do not by themselves improve reconstruction accuracy.

Introduction

Many computational tasks involving parametric partial differential equations (PDEs) require repeated evaluation of the same parameter-to-solution or parameter-to-observable map. Examples include uncertainty quantification, PDE-constrained optimisation and control, experimental design and parameter identification. When of a large-scale PDE, the cost can become prohibitive, particularly when sensitivities of the forward map are needed as well as its values.

Neural operators offer one way of amortising this cost. A neural operator is trained offline to approximate a map between function spaces and is then evaluated at comparatively low online cost [23] (Lu et al. 2021; Li et al. 2021). Learned operators have been embedded in PDE-constrained optimisation and control [17], Bayesian experimental design (Go and Chen, 2025) and Bayesian parameter identification, where posterior exploration requires many forward and derivative evaluations [5]. Derivative-informed surrogates developed for such many-query settings learn the forward map together with its derivative [30, 31]. Neural-operator surrogates have also been used in ensemble-based inversion of moving-boundary problems [18].

Neural operators can also be trained to map observations directly to the unknown parameters. Neural Inverse Operators, introduced by Molinaro et al. [28], learn operator-to-function maps for PDE inverse problems with operator-valued measurements. For the Calderón problem, de Hoop et al. [8] construct a noise-aware neural-operator approximation using an extension of the inverse conductivity map that preserves its stability properties. In inverse imaging, Auras et al. [3] interpret U-Nets, which are widely used to post-process a crude reconstruction such as the backprojected data, as neural operators, and study how such networks behave when the discretisation is refined, with limited-angle computed tomography as the application. These approaches rely on structure, or on a regularised input, that keeps the learned inverse map stable on the class of interest. Without such structure, the inverse map of an ill-posed problem is unstable, and this has a direct consequence for neural approximation (Proposition 2.2 in § 2). No continuous network can approximate a discontinuous inverse map uniformly near a point of discontinuity to within half the size of the jump, and networks that are accurate on training data resolving the discontinuity must have Lipschitz constants that grow without bound. For Fourier neural operators of fixed depth, some weights must then diverge. In this work we therefore learn the forward map, which in PDE parameter identification is typically continuously differentiable, and control the instability of the inversion by regularisation.

On the other hand, the use of learned forward maps within classical regularisation of ill-posed inverse problems has received less attention. In this setting the learned operator is part of the regularisation method itself, and replacing the forward map by an approximation may alter stability, convergence and the criterion by which the iteration should be stopped. Scherzer et al. [36] study Tikhonov regularisation with an approximate neural forward operator and show how observational and operator errors must be balanced with the regularisation parameter. Landweber-type iterations with perturbed or noisy forward operators have also been analysed (e.g. Gu et al., 2025), and learned components have been combined with Landweber iteration [2]. To our knowledge, however, the use of neural-operator surrogates within iterative regularisation, where the derivatives that determine the search directions are also approximate, remains largely unexplored.

Iterative regularisation methods evaluate the forward map and, for derivative-based schemes, its linearisation or adjoint at every step. When these operations are expensive, replacing them by a differentiable learned operator could reduce the online cost substantially once the offline training cost has been amortised. This is most relevant when many related inverse problems must be solved, or when reconstructions are needed quickly, for example in real-time monitoring. We study this question for nonlinear Landweber iteration. Landweber is among the simplest derivative-based iterative regularisation methods and is typically slower than Newton, Gauss–Newton or Levenberg–Marquardt-type schemes. Inexpensive surrogate evaluations change the balance between iteration count and cost per iteration, which makes this slower method more attractive. Landweber iteration also provides a transparent setting in which the effect of approximating both the forward map and its derivative can be analysed. The analysis is formulated for nonlinear maps between Hilbert spaces, and PDE parameter identification provides the computational motivation and the numerical examples.

Let M\mathcal{M} and Y\mathcal{Y} be real separable Hilbert spaces and let F:dom⁡(F)⊆M⟶Y\mathcal{F} : \operatorname{dom}(\mathcal{F}) \subseteq\mathcal{M} \longrightarrow\mathcal{Y} denote the forward operator. Given exact data y†=F(m†)y^\dagger= \mathcal{F}(m^\dagger) and noisy observations yδy^\delta satisfying

∥yδ−y†∥Y≤δ,(1)\lVert y^\delta- y^\dagger\rVert_{\mathcal{Y}} \le\delta, \tag*{(1)}

the nonlinear Landweber iteration takes the form

mk+1=mk−ωDF(mk)∗(F(mk)−yδ),(2)m_{k+1} = m_k - \omega D\mathcal{F}(m_k)^*(\mathcal{F}(m_k)-y^\delta), \tag*{(2)}

together with a stopping rule. Under standard local assumptions, including a tangential cone condition, Landweber iteration stopped by the discrepancy principle is a regularisation method for nonlinear ill-posed problems [15, 11, 19]. As the iteration formula (2) shows, the Landweber iteration is an explicit regularisation method that involves only the forward mapping and its linearisation, both of which can be well approximated by suitable learned neural operators. Replacing F\mathcal{F} by a differentiable learned operator Fθ\mathcal{F}_\theta, and differentiating the same surrogate, gives

mk+1=mk−ωDFθ(mk)∗(Fθ(mk)−yδ).(3)m_{k+1} = m_k - \omega D\mathcal{F}_\theta(m_k)^*(\mathcal{F}_\theta(m_k)-y^\delta). \tag*{(3)}

The central question of this paper is whether this substitution preserves the regularising properties of the original method.

Two approximation errors enter the iteration. Error in Fθ\mathcal{F}_\theta perturbs the residual against which the data are fitted, and error in DFθD\mathcal{F}_\theta perturbs the direction in which the parameter is updated. Accurate forward prediction alone is therefore not sufficient, because a surrogate with inaccurate derivatives may produce poor Landweber directions. The usual discrepancy principle also cannot be applied unchanged, since a small residual for Fθ\mathcal{F}_\theta need not imply that the physical forward equation is satisfied to the same accuracy.

Our contributions are as follows.

  • We show that near a discontinuity, no continuous neural network can uniformly approximate a discontinuous inverse map, which renders neural operator surrogates for the inverse map infeasible (§ 2). Meanwhile, we identify encoder–network–decoder neural operators that approximate a nonlinear forward map and its derivative simultaneously, first along compact sets of directions and then, for compact derivatives, in operator norm (§ 3). Generalised DeepONets and fully coupled Fourier operators realise this class exactly (§ 4).

  • For a surrogate with separate forward and derivative error bounds, we introduce an effective discrepancy level that accounts for observational, forward and derivative errors,

and prove descent before stopping and finite termination of the resulting discrepancy principle (§ 5).

  • We prove convergence of the stopped reconstructions as the data and surrogate errors vanish for the preconditioned iteration

mk+1=mk−ωCDFθ(mk)∗(Fθ(mk)−yδ)m_{k+1} = m_k - \omega C D F_\theta(m_k)^* \left(F_\theta(m_k) - y^\delta\right)

with a compact operator CC (Theorem 5.15). Closed balls of the Hilbert space MC\mathcal{M}_C induced by CC are compact in M\mathcal{M}, descent in the MC\mathcal{M}_C norm keeps the iterates in such a ball, and the approximation theory supplies surrogates that are accurate on it. The price is the regularity condition m†−m0∈MCm^\dagger- m_0 \in\mathcal{M}_C. Without a compact preconditioner, the descent argument still applies wherever the error bounds hold, but the iterates are no longer confined to a compact set and convergence as the errors vanish is not established.

  • We relate these requirements to practical derivative-informed training (§ 6). Supervision along a finite set of directions controls a finite-rank part of the derivative error, whereas the preconditioned iteration depends on the weighted error (DFθ−DF)C1/2(D F_\theta- D F)C^{1/2}. Smoothing can attenuate poorly learned components of the search direction, but it also suppresses genuine fine-scale features and restricts the truths covered by the theory.

  • We study these effects numerically for the identification of a reaction coefficient in an elliptic PDE (§ 7), comparing standard and generalised architectures, training with and without the derivative loss, and different parameter-space geometries. The networks are trained with derivatives along a fixed set of empirical Karhunen–Loève (KL) directions, which is one practical choice among several covariance-, sensitivity- or random-projection-based options ([31, 34, 39, 27]). Transient Darcy-flow inversion with sparse space–time data (§ 7.12) illustrates the approach in a time-dependent setting with a standard architecture.

Conclusions and directions for further work are given in § 8. The appendices contain the approximation proofs, the standard Fourier Neural Operator (FNO) calculus and the proofs for the preconditioned geometry.

Learning a discontinuous inverse map

This section formalizes the statement made in the introduction that directly learning a discontinuous inverse map is unstable, thereby establishing the necessity of our proposed approach, which uses a neural-network-surrogated Landweber iteration to solve inverse problems stably.

Let R:dom⁡(R)⊆Y→M\mathcal{R} : \operatorname{dom}(\mathcal{R}) \subseteq\mathcal{Y} \to\mathcal{M} be an inversion or reconstruction map, for example, R=F−1\mathcal{R} = \mathcal{F}^{-1} on the range of an injective forward operator. The following is a formal definition of such a discontinuous operator.

Definition 2.1 (Discontinuous map). The map R\mathcal{R} is discontinuous at y0∈dom⁡(R)y_0 \in\operatorname{dom}(\mathcal{R}) if there exist a constant C>0C > 0 and a sequence {yn}⊂dom⁡(R)\{y_n\} \subset\operatorname{dom}(\mathcal{R}) such that yn→y0y_n \to y_0 in Y\mathcal{Y}, yn≠y0y_n \ne y_0 for all nn, and

∥R(yn)−R(y0)∥M≥Cfor all n.\lVert\mathcal{R}(y_n)-\mathcal{R}(y_0)\rVert_{\mathcal{M}} \ge C \quad\text{for all } n.

Consequently, the following proposition shows that no continuous map can accurately approximate a discontinuous map, including Lipschitz continuous maps and generic neural operators. For simplicity, we prove the result only for FNO, but the argument holds for other architectures such as DeepONet.

Proposition 2.2 (Weight Blow-Up in Approximation of Discontinuous Maps). Let R\mathcal{R} be discontinuous at y0y_0, with CC and {yn}\{y_n\} as in Definition 2.1. Then the following hold.

(i) Let G:dom⁡(R)→MG : \operatorname{dom}(\mathcal{R}) \to\mathcal{M} be continuous at y0y_0. If ∥G(y)−R(y)∥M≤ϵ\lVert G(y)-\mathcal{R}(y)\rVert_{\mathcal{M}} \le\epsilon for y=y0y=y_0 and for all yny_n, then there holds ϵ≥C/2>0\epsilon\ge C/2 > 0.

(ii) Let 0≤ϵ1<C/20 \le\epsilon_1 < C/2, and for each nn let Gn:dom⁡(R)→MG_n : \operatorname{dom}(\mathcal{R}) \to\mathcal{M} be Lipschitz continuous with ∥Gn(y)−R(y)∥M≤ϵ1\lVert G_n(y)-\mathcal{R}(y)\rVert_{\mathcal{M}} \le\epsilon_1 for y∈{y0,yn}y \in\{y_0,y_n\}. Then

Lip⁡(Gn)≥C−2ϵ1∥yn−y0∥Y⟶∞.\operatorname{Lip}(G_n) \ge\frac{C-2\epsilon_1}{\lVert y_n-y_0\rVert_{\mathcal{Y}}} \longrightarrow\infty.

(iii) Suppose, in (ii), that each GnG_n is a standard FNO with fixed depth and a globally Lipschitz activation, and that its lifting and projection networks have fixed depth. Let Y\mathcal{Y} and M\mathcal{M} carry the L2L^2 or grid norms in which (51) in Appendix § 12 holds. Then at least one of the weight-matrix or Fourier-multiplier norms in (51) is unbounded as n→∞n \to\infty.

Proof. The first two arguments are well known in inverse problems, and we briefly outline the proof below. For any map GG and any nn, the following inequality holds:

C≤∥R(yn)−R(y0)∥M≤∥R(yn)−G(yn)∥M+∥G(yn)−G(y0)∥M+∥G(y0)−R(y0)∥M.C \le\lVert\mathcal{R}(y_n)-\mathcal{R}(y_0)\rVert_{\mathcal{M}} \le\lVert\mathcal{R}(y_n)-G(y_n)\rVert_{\mathcal{M}}+\lVert G(y_n)-G(y_0)\rVert_{\mathcal{M}}+\lVert G(y_0)-\mathcal{R}(y_0)\rVert_{\mathcal{M}}.

Then we can prove: (i) the right-hand side is at most 2ϵ+∥G(yn)−G(y0)∥M2\epsilon+\lVert G(y_n)-G(y_0)\rVert_{\mathcal{M}}, which tends to 2ϵ2\epsilon as n→∞n \to\infty by continuity of GG at y0y_0. Hence ϵ≥C/2>0\epsilon\ge C/2 > 0.

(ii) Choosing G=GnG=G_n, we see that the right-hand side of the above inequality is at most 2ϵ1+Lip⁡(Gn)∥yn−y0∥Y2\epsilon_1+\operatorname{Lip}(G_n)\lVert y_n-y_0\rVert_{\mathcal{Y}}. Rearranging yields a lower bound on Lip⁡(Gn)\operatorname{Lip}(G_n) whose right-hand side diverges as yn→y0y_n \to y_0, since C−2ϵ1>0C-2\epsilon_1 > 0.

(iii) By deriving the Lipschitz constant for FNO, as shown in the right-hand side of (51) in Appendix § 12, it is a product of the listed norms and fixed constants. If all these norms were bounded in nn, so would be Lip⁡(Gn)\operatorname{Lip}(G_n), which contradicts the result of (ii).

As we argued in the introduction and above, a neural operator cannot accurately approximate a discontinuous map, which in inverse problems is typically the inversion map. Nevertheless, we prove in the next section that if the forward map is well-posed, then generic neural operators can approximate the forward map and its linearisation to a certain accuracy.

Simultaneous approximation of the forward map and its derivative

Our proposed surrogate Landweber iteration (3) uses both the forward map and the adjoint of its derivative, so we need neural operators that approximate both at once. We work with a reduced-basis class built from a bounded linear encoder, a finite-dimensional neural network and a bounded linear decoder. We first approximate derivative actions on compact sets of directions, and then, under additional assumptions, the derivative in operator norm, which is the bound used in § 5.

In this section, we allow M\mathcal{M} and Y\mathcal{Y} to be Banach spaces. The error-bound analysis of the surrogate Landweber iteration (3) in § 5 is carried out in Hilbert spaces, but it can be extended to Banach spaces by adapting the convergence analysis of Schuster et al. [37]. An operator in the reduced-basis class has the form

Fθ(m)=Φfθ(Ψm),Ψ∈L(M,Rr),Φ∈L(Rs,Y).(4)F_{\theta}(m) = \Phi f_{\theta}(\Psi m), \qquad\Psi\in\mathcal{L}(\mathcal{M},\mathbb{R}^{r}), \qquad\Phi\in\mathcal{L}(\mathbb{R}^{s},\mathcal{Y}). \tag*{(4)}

Here, the bounded linear encoder Ψ\Psi maps the input mm to rr coordinates, the finite neural network fθ:Rr→Rsf_{\theta} : \mathbb{R}^{r} \to\mathbb{R}^{s} maps these to ss output coefficients, and the bounded linear decoder Φ\Phi reconstructs an element of Y\mathcal{Y} from those coefficients. In the approximation results, the encoder, the decoder and their dimensions are chosen together with the network, so greater accuracy may require richer input and output representations as well as a larger network.

For the finite-dimensional network fθf_{\theta}, we use a nonpolynomial activation σ∈C1(R)\sigma\in C^{1}(\mathbb{R}), such as GELU or tanh. Networks with this activation can approximate a finite-dimensional C1C^{1} map and its first derivative uniformly on compact sets ([16, 33]). This is the finite-dimensional step in the constructions below, and Lemma A.4 in Appendix § 11 states the version used here.

Compact direction sets

de Feo [7] shows that encoder–decoder neural operators, a class that includes DeepONets, approximate a globally defined operator in his class CBkC^{k}_{B} and its first kk derivatives simultaneously on compact sets of inputs and directions. Theorem 3.1 gives a local, first-derivative version of this result for forward maps defined on an open subset of the input space. Appendix § 11 provides a self-contained proof and the corresponding encoder–network–decoder construction.

A Banach space has the approximation property if its identity can be approximated uniformly on every compact set by bounded finite-rank maps. In the theorem below, this property provides finite-dimensional representations of the inputs and directions in M\mathcal{M} and of the corresponding values and derivative outputs in Y\mathcal{Y}.

For standard FNOs, simultaneous approximation of an operator and its derivative is established by Yao et al. [39]. § 4.3 compares that result with the ones below.

Theorem 3.1 (Approximation on compact inputs and directions). Suppose M\mathcal{M} and Y\mathcal{Y} have the approximation property as defined in Definition A.1, U⊂MU \subset\mathcal{M} is open, and F∈C1(U,Y)\mathcal{F} \in C^{1}(U,\mathcal{Y}). Let K⊂U\mathcal{K} \subset U and H⊂MH \subset\mathcal{M} be compact. For every ϵ>0\epsilon> 0, there exists an operator of the form (4) such that

sup⁡m∈K∥F(m)−Fθ(m)∥Y<ϵ.(5)\sup_{m \in\mathcal{K}} \lVert\mathcal{F}(m)-\mathcal{F}_{\theta}(m)\rVert_{\mathcal{Y}} < \epsilon. \tag*{(5)}
sup⁡m∈Kh∈H∥DF(m)h−DFθ(m)h∥Y<ϵ.(6)\sup_{\substack{m \in\mathcal{K}\\h\in H}} \lVert D\mathcal{F}(m)h-D\mathcal{F}_{\theta}(m)h\rVert_{\mathcal{Y}} < \epsilon. \tag*{(6)}

Proof. See Appendix A.2.

Approximation of derivatives in operator norm

Theorem 3.1 controls the derivative error along a prescribed compact set of directions. The Landweber analysis in § 5 requires a bound over all directions of norm at most one, that is, in the operator norm

References

  1. [1]F. Albiac and N. J. Kalton. Topics in Banach Space Theory. Springer, 2006.
  2. [2]A. Aspri, S. Baner, O. Öktem, and O. Scherzer. A data-driven iteratively regularized Landweber iteration. Numerical Functional Analysis and Optimization, 41(10):1190–1227, 2020.DOI
  3. [3]A. Auras, M. Burger, S. Kabri, M. Moeller, and M. Schopf-Kuester. A neural operator view on U-Nets for inverse imaging problems, 2026. arXiv:2608.05839.arxiv.org/abs/2608.05839
  4. [4]K. Bhattacharya, B. Hosseini, N. B. Kovachki, and A. M. Stuart. Model reduction and neural networks for parametric PDEs. The SMAI Journal of Computational Mathematics, 7:121–157, 2021.arxiv.org/abs/2005.03180
  5. [5]L. Cao, T. O’Leary-Roseberry, and O. Ghattas. Derivative-informed neural operator acceleration of geometric MCMC for infinite-dimensional Bayesian inverse problems. Journal of Machine Learning Research, 26(78):1–68, 2025.arxiv.org/abs/2403.08220
  6. [6]A. Colagrande, P. Caillon, E. Feillet, and A. Allauzen. Higher-order Fourier neural operator: Explicit mode mixer for nonlinear PDEs. arXiv:2606.28122, 2026.arxiv.org/abs/2606.28122
  7. [7]F. de Feo. Universal approximation of nonlinear operators and their derivatives. arXiv:2605.15285v3, 2026.arxiv.org/abs/2605.15285
  8. [8]M. V. de Hoop, N. B. Kovachki, M. Lassas, and N. H. Nelsen. Extension and neural operator approximation of the electrical impedance tomography inverse map. arXiv:2511.20361, 2025.arxiv.org/abs/2511.20361
  9. [10]H. Egger and A. Neubauer. Preconditioning Landweber iteration in Hilbert scales. Numerische Mathematik, 101(4):643–662, 2005.DOI
  10. [11]H. W. Engl, M. Hanke, and A. Neubauer. Regularization of Inverse Problems. Kluwer Academic Publishers, 1996.
  11. [12]V. S. Fanaskov and I. V. Oseledets. Spectral neural operators. Doklady Mathematics, 108 (Suppl 2):S226–S232, 2023.
  12. [15]M. Hanke, A. Neubauer, and O. Scherzer. A convergence analysis of the Landweber iteration for nonlinear ill-posed problems. Numerische Mathematik, 72:21–37, 1995.DOI
  13. [16]K. Hornik, M. Stinchcombe, and H. White. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 3(5):551–560, 1990.DOI
  14. [17]R. Hwang, J. Y. Lee, J. Y. Shin, and H. J. Hwang. Solving PDE-constrained control problems using operator learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4):4504–4512, 2022.
  15. [18]M. A. Iglesias, M. E. Causon, M. Y. Matveev, A. Endrewit, and M. V. Tretyakov. DeepONet-accelerated Bayesian inversion for moving boundary problems. Computer Methods in Applied Mechanics and Engineering, 457:118988, 2026.
  16. [19]B. Kaltenbacher, A. Neubauer, and O. Scherzer. Iterative Regularization Methods for Nonlinear Ill-Posed Problems. Walter de Gruyter, 2008.
  17. [20]M. Kanagawa, P. Hennig, D. Sejdinovic, and B. K. Sriperumbudur. Gaussian processes and kernel methods: A review on connections and equivalences. arXiv:1807.02582, 2018.arxiv.org/abs/1807.02582
  18. [23]N. Kovachki, Z. Li, B. Liu, K. Azizzadenesheli, K. Bhattacharya, A. Stuart, and A. Anandkumar. Neural operator: Learning maps between function spaces with applications to PDEs. Journal of Machine Learning Research, 24(89):1–97, 2023.
  19. [24]Z. Li, N. Kovachki, K. Azizzadenesheli, B. Liu, K. Bhattacharya, A. Stuart, and A. Anandkumar. Fourier neural operator for parametric partial differential equations. In International Conference on Learning Representations, 2021.
  20. [27]D. Luo, T. O’Leary-Roseberry, P. Chen, and O. Ghattas. Dimension reduction for derivative-informed operator learning: An analysis of approximation errors. Journal of Machine Learning Research, 27(182):1–94, 2026.arxiv.org/abs/2504.08730
  21. [28]R. Molinaro, Y. Yang, B. Engquist, and S. Mishra. Neural inverse operators for solving PDE inverse problems. In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 25105–25139, 2023.arxiv.org/abs/2301.11167
  22. [29]A. Neubauer. On Landweber iteration for nonlinear ill-posed problems in Hilbert scales. Numerische Mathematik, 85(2):309–328, 2000.DOI
  23. [30]T. O’Leary-Roseberry, U. Villa, P. Chen, and O. Ghattas. Derivative-informed projected neural networks for high-dimensional parametric maps governed by PDEs. Computer Methods in Applied Mechanics and Engineering, 388:114199, 2022.
  24. [31]T. O’Leary-Roseberry, P. Chen, U. Villa, and O. Ghattas. Derivative-informed neural operator: An efficient framework for high-dimensional parametric derivative learning. Journal of Computational Physics, 496:112555, 2024.
  25. [32]M. Piana and M. Bertero. Projected Landweber method and preconditioning. Inverse Problems, 13(2):441–463, 1997.DOI
  26. [33]A. Pinkus. Approximation theory of the MLP model in neural networks. Acta Numerica, 8:143–195, 1999.DOI
  27. [34]Y. Qiu, N. Bridges, and P. Chen. Derivative-enhanced deep operator network. In Advances in Neural Information Processing Systems, volume 37, 2024.arxiv.org/abs/2402.19242
  28. [35]C. E. Rasmussen and C. K. I. Williams. Gaussian Processes for Machine Learning. The MIT Press, 2006.DOI
  29. [36]O. Scherzer, T. L. N. Vu, and J. Yan. Neural operators for solving nonlinear inverse problems. Numerical Functional Analysis and Optimization, 2026.arxiv.org/abs/2508.19347
  30. [37]T. Schuster, B. Kaltenbacher, B. Hofmann, and K. S. Kazimierski. Regularization methods in Banach spaces, volume 10 of Radon Series on Computational and Applied Mathematics. Walter de Gruyter GmbH & Co. KG, Berlin, 2012. ISBN 978-3-11-025524-9.DOI
  31. [38]H. Wendland. Scattered Data Approximation. Cambridge University Press, 2005.DOI
  32. [39]B. Yao, D. Luo, L. Cao, N. Kovachki, T. O’Leary-Roseberry, and O. Ghattas. Derivative-informed Fourier neural operator: Universal approximation and applications to PDE-constrained optimization. arXiv:2512.14086v2, 2025.arxiv.org/abs/2512.14086

Paper details

vlnc:W_b3z8vk6q
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

ChatGPT, Codex, Claude

View statement
Looking for related papers…
Contents