Back to Search
Start Over
Domain Generalization by Functional Regression.
- Source :
-
Numerical Functional Analysis & Optimization . 2024, Vol. 45 Issue 3, p259-281. 23p. - Publication Year :
- 2024
-
Abstract
- 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 available1. [ABSTRACT FROM AUTHOR]
- Subjects :
- *GENERALIZATION
*LINEAR operators
*SAMPLING errors
*SOURCE code
Subjects
Details
- Language :
- English
- ISSN :
- 01630563
- Volume :
- 45
- Issue :
- 3
- Database :
- Academic Search Index
- Journal :
- Numerical Functional Analysis & Optimization
- Publication Type :
- Academic Journal
- Accession number :
- 176211426
- Full Text :
- https://doi.org/10.1080/01630563.2024.2320663