Metraipolis › archive › dc_f62dffabbaf9
Data-driven Regularization for Inverse Problems — arXiv:2610.40048
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.40048
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:32:28.220Z
- SHA-256 of the archived text
d0ebb20178abf656e03b1df1e06d831f55fcd7dbec3ad20b62afbb967eda53dc- Stable URL of this page
https://metraipolis.com/documento/dc_f62dffabbaf9
How to cite
Data-driven Regularization for Inverse Problems — arXiv:2610.40048 — arXiv (en), https://arxiv.org/abs/2610.40048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f62dffabbaf9 (Metraipolis archive dc_f62dffabbaf9, sha256 d0ebb20178abf656e03b1df1e06d831f55fcd7dbec3ad20b62afbb967eda53dc)
BibTeX
@misc{dcf62dffabbaf9,
title = {Data-driven Regularization for Inverse Problems — arXiv:2610.40048},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.40048},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f62dffabbaf9; sha256 d0ebb20178abf656e03b1df1e06d831f55fcd7dbec3ad20b62afbb967eda53dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In many applications, we are interested in studying an object of interest $x$. However, its properties are often not directly measurable. Instead, we only observe $y = F(x)$, where the (known) function $F$ is referred to as the forward mapping. To infer about $x$ from the observation $y$, we seek an (approximate) inverse mapping $x \approx F^{-1}(y)$. This process is known as solving the inverse problem. In practice, the inverse mapping $F^{-1}$ may be ill-defined or discontinuous, which forces us to choose a certain solution from many possible ones based on prior assumptions on $x$. Such assumptions about $x$ are typically incorporated into the inversion process through regularization. Therefore, the first part of this course focuses on the classical regularization theory of inverse problems. In the second part, we transition to algorithmic approaches for solving inverse problems. The foundation for this lies in the variational formulation of inverse problems, where reconstructions are obtained by minimizing specific functionals. Here, we will explore key optimization principles, discuss their practical implementation, and examine how they contribute to robust reconstructions. Today, classical methods are often modified to incorporate data-driven machine learning techniques, which improve the empirical performance. However, this often comes at the cost of explainability or convergence guarantees. Such properties are critical, for example, in medical applications, where one wants to be confident that reconstructed abnormalities are of physical nature and not phantoms resulting from the method. For these reasons, we discuss a number of machine learning methods for inverse problems, such as unrolling techniques, learned regularizers and plug-and-play methods, and explore their performance guarantees.
Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Numerical Analysis (math.NA) ; Functional Analysis (math.FA); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.40048 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:14:28.354Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).