Domain Generalization by Functional Regression

DOI10.1080/01630563.2024.2320663MaRDI QIDQ6130669zbMATH OpenOpenAlexFDO

Authors Markus Holzleitner, Sergei V. Pereverzyev, Werner Zellinger

Publication date 3 April 2024

Published in Numerical Functional Analysis and Optimization (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2302.04724

zbMATH Keywords

reproducing kernel Hilbert spacefinite sample boundsdomain generalizationoperator learningfunction-to-function regression

Mathematics Subject Classification ID

Statistics (62-XX) Computer science (68-XX)

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.

Cites work

• scientific article; zbMATH DE number 1804115 (Why is no real title available?)
• scientific article; zbMATH DE number 936298 (Why is no real title available?)
• scientific article; zbMATH DE number 7370519 (Why is no real title available?)
• Algorithmic stability and meta-learning
• Hilbert space embeddings and metrics on probability measures
• Learning multiple tasks with kernel methods
• Learning theory for distribution regression
• Learning theory of distributed spectral algorithms
• NIST handbook of mathematical functions
• Non-asymptotic error bound for optimal prediction of function-on-function regression by RKHS approach
• On a regularization of unsupervised domain adaptation in RKHS
• On the mathematical foundations of learning
• Optimal rates for the regularized least-squares algorithm
• Optimum bounds for the distributions of martingales in Banach spaces
• Real Analysis and Probability

Cited in

(2)

• On the convergence of gradient descent for robust functional linear regression
• An accelerated inexact Newton regularization scheme with a learned feature-selection rule for non-linear inverse problems

This page was built for publication: Domain Generalization by Functional Regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6130669)