Neural operators for solving nonlinear inverse problems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915980290031616 |
|---|---|
| author | Scherzer, Otmar Vu, Thi Lan Nhi Yan, Jikai |
| author_facet | Scherzer, Otmar Vu, Thi Lan Nhi Yan, Jikai |
| contents | We consider solving a probably infinite dimensional operator equation, where the operator is not modeled by physical laws but is specified indirectly via training pairs of the input-output relation of the operator. Neural operators have proven to be efficient to approximate infinite dimensional operators. In this paper we analyze Tikhonov regularization with neural operators as surrogates for solving ill-posed operator equations. The analysis is based on balancing approximation errors of neural operators, regularization parameters, and noise. Moreover, we extend the approximation properties of neural operators from sets of continuous functions to Sobolev and Lebesgue spaces, which is crucial for solving inverse problems and we discuss the problem of finding an appropriate network structure of neural operators (training). Finally, we present some numerical experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19347 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Neural operators for solving nonlinear inverse problems Scherzer, Otmar Vu, Thi Lan Nhi Yan, Jikai Numerical Analysis Functional Analysis We consider solving a probably infinite dimensional operator equation, where the operator is not modeled by physical laws but is specified indirectly via training pairs of the input-output relation of the operator. Neural operators have proven to be efficient to approximate infinite dimensional operators. In this paper we analyze Tikhonov regularization with neural operators as surrogates for solving ill-posed operator equations. The analysis is based on balancing approximation errors of neural operators, regularization parameters, and noise. Moreover, we extend the approximation properties of neural operators from sets of continuous functions to Sobolev and Lebesgue spaces, which is crucial for solving inverse problems and we discuss the problem of finding an appropriate network structure of neural operators (training). Finally, we present some numerical experiments. |
| title | Neural operators for solving nonlinear inverse problems |
| topic | Numerical Analysis Functional Analysis |
| url | https://arxiv.org/abs/2508.19347 |