A unifying representer theorem for inverse problems and machine learning (Q2231644): Difference between revisions
From MaRDI portal
Created claim: Wikidata QID (P12): Q130240264, #quickstatements; #temporary_batch_1730771136365 |
Normalize DOI. |
||
| Property / DOI | |||
| Property / DOI: 10.1007/s10208-020-09472-x / rank | |||
| Property / DOI | |||
| Property / DOI: 10.1007/S10208-020-09472-X / rank | |||
Normal rank | |||
Latest revision as of 14:28, 17 December 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A unifying representer theorem for inverse problems and machine learning |
scientific article |
Statements
A unifying representer theorem for inverse problems and machine learning (English)
0 references
30 September 2021
0 references
A novel higher-level formulation of regularization is proposed in the context of Banach spaces. A general representer theorem for characterizing the solutions of a broad class of optimization problems is proven and then shown to be employable for rediscovering various known similar results from the literature.
0 references
convex optimization
0 references
regularization
0 references
representer theorem
0 references
inverse problem
0 references
machine learning
0 references
Banach space
0 references
0 references
0 references
