Domain Generalization by Functional Regression

Markus Holzleitner, Sergei V. Pereverzyev, Werner Zellinger
2/9/2023
cs.LGmath.STstat.ML

No official code found. Best implementation: wzell/FuncRegr4DomGen (3 stars, MIT, last commit 2023-07-21).

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 available.

View on arXivView PDF

Code Implementations(1)

wzell/FuncRegr4DomGenCommunity100%
MIT
32PythonJan 27, 20233 years agoMIT

Similar Papers

Bayesian Kernel Regression for Functional Data

82% match2025

Rethinking Multi-Domain Generalization with A General Learning Objective

80% match1 repo212026

Learning Functional Transduction

79% match2023

Towards regularized learning from functional data with covariate shift

79% match2026

COD: Learning Conditional Invariant Representation for Domain Adaptation Regression

79% match1 repo2024

Domain Agnostic Conditional Invariant Predictions for Domain Generalization

78% match2024

Cite this paper

@article{holzleitner2023domain,
  title  = {Domain Generalization by Functional Regression},
  author = {Markus Holzleitner and Sergei V. Pereverzyev and Werner Zellinger},
  year   = {2023},
  eprint = {2302.04724},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.04724v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.04724.svg)](https://codeofpaper.com/paper/2302.04724)

Discussion