Improved learning theory for kernel distribution regression with two-stage sampling
The Annals of Statistics · 01.08.2025 · 53 (4) · 1753-1782
DOI: 10.1214/25-aos2537 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Annals of Statistics, erschienen am 01.08.2025. Verfasst von François Bachoc und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 83 Literaturangaben.
Abstract (Originalsprache)
The distribution regression problem encompasses many important statistics and machine learning tasks, and arises in a large range of applications. Among various existing approaches to tackle this problem, kernel methods have become a method of choice. Indeed, kernel distribution regression is both computationally favorable, and supported by a recent learning theory. This theory also tackles the two-stage sampling setting, where only samples from the input distributions are available. In this paper, we improve the learning theory of kernel distribution regression. We address kernels based on Hilbertian embeddings that encompass most, if not all, of the existing approaches. We introduce the novel near-unbiased condition on the Hilbertian embeddings that enables us to provide new error bounds on the effect of the two-stage sampling, thanks to a new analysis. We show that this near-unbiased condition holds for three important classes of kernels, based on optimal transport and mean embedding. As a consequence, we strictly improve the existing convergence rates for these kernels. Our setting and results are illustrated by numerical experiments.
Zitieren
APA
Bachoc, F., Béthune, L., González-Sanz, A., & Loubes, J. (2025). Improved learning theory for kernel distribution regression with two-stage sampling. The Annals of Statistics, 53(4), 1753-1782. https://doi.org/10.1214/25-aos2537
Vancouver
Bachoc F, Béthune L, González-Sanz A, Loubes J. Improved learning theory for kernel distribution regression with two-stage sampling. The Annals of Statistics. 2025;53(4):1753-1782. doi:10.1214/25-aos2537
BibTeX
@article{Bachoc2025,
author = {Bachoc, François and Béthune, Louis and González-Sanz, Alberto and Loubes, Jean-Michel},
title = {Improved learning theory for kernel distribution regression with two-stage sampling},
journal = {The Annals of Statistics},
year = {2025},
volume = {53},
number = {4},
pages = {1753--1782},
doi = {10.1214/25-aos2537}
}
EUVIMED