Domain Generalization by Functional Regression
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911791962914816 |
|---|---|
| author | Holzleitner, Markus Pereverzyev, Sergei V. Zellinger, Werner |
| author_facet | Holzleitner, Markus Pereverzyev, Sergei V. Zellinger, Werner |
| contents | The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples. In this paper, we study domain generalization as a problem of functional regression. Our concept leads to a new algorithm for learning a linear operator from marginal distributions of inputs to the corresponding conditional distributions of outputs given inputs. Our algorithm allows a source distribution-dependent construction of reproducing kernel Hilbert spaces for prediction, and, satisfies finite sample error bounds for the idealized risk. Numerical implementations and source code are available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_04724 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Domain Generalization by Functional Regression Holzleitner, Markus Pereverzyev, Sergei V. Zellinger, Werner Machine Learning Statistics Theory 68Q32 The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples. In this paper, we study domain generalization as a problem of functional regression. Our concept leads to a new algorithm for learning a linear operator from marginal distributions of inputs to the corresponding conditional distributions of outputs given inputs. Our algorithm allows a source distribution-dependent construction of reproducing kernel Hilbert spaces for prediction, and, satisfies finite sample error bounds for the idealized risk. Numerical implementations and source code are available. |
| title | Domain Generalization by Functional Regression |
| topic | Machine Learning Statistics Theory 68Q32 |
| url | https://arxiv.org/abs/2302.04724 |