Semi-Supervised Kernel Ridge Fréchet Regression
Abstract
Fréchet regression provides a framework for predicting random object-valued responses by minimizing the conditional expected squared distances. We propose semi-supervised kernel ridge Fréchet regression (SS-KRFR) to exploit unlabeled covariates when labeled samples are scarce. The method learns kernel spectral features from both labeled and unlabeled covariates, then utilizes labeled responses to estimate the conditional Fréchet function by kernel ridge regression. We derive prediction error bounds that distinguish the roles of labeled and unlabeled samples, and establish polynomial convergence rates under suitable conditions. Under additional kernel assumptions, a sharper analysis relaxes the sample size requirements for learning the features. We also develop hybrids that combine features, predictions, or both from models fitted with and without unlabeled covariates, establishing uniform stability over mixing weights in Hadamard spaces at common tuning and a separate rate guarantee for prediction mixing. Simulations and a real-data application show semi-supervised gains and improvements over competing Fréchet regression methods in several settings.
Related
- Robust Error Bounds for Vector-Valued Kernel Ridge Regression
- Kernel Ridge Regression over Hölder Classes: Function and Derivative Losses
- Infinite-Dimensional Spherical Kernel ridge Regression
- Learning Closure of Dynamical Systems with Kernel Ridge Regression
- Elastic kernel Ridge regression, with applications in phonetics
BibTeX
@misc{seo2026semisupervised,
title = {{Semi-Supervised Kernel Ridge Fréchet Regression}},
author = {Jaehee Seo and Kwangho Kim and Jisu Kim},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.05388},
eprint = {2610.05388},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.05388},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Semi-Supervised Kernel Ridge Fréchet Regression
AU - Jaehee Seo
AU - Kwangho Kim
AU - Jisu Kim
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.05388
UR - https://arxiv.org/abs/2610.05388
AB - Fréchet regression provides a framework for predicting random object-valued responses by minimizing the conditional expected squared distances. We propose semi-supervised kernel ridge Fréchet regression (SS-KRFR) to exploit unlabeled covariates when labeled samples are scarce. The method learns kernel spectral features from both labeled and unlabeled covariates, then utilizes labeled responses to estimate the conditional Fréchet function by kernel ridge regression. We derive prediction error bounds that distinguish the roles of labeled and unlabeled samples, and establish polynomial convergence rates under suitable conditions. Under additional kernel assumptions, a sharper analysis relaxes the sample size requirements for learning the features. We also develop hybrids that combine features, predictions, or both from models fitted with and without unlabeled covariates, establishing uniform stability over mixing weights in Hadamard spaces at common tuning and a separate rate guarantee for prediction mixing. Simulations and a real-data application show semi-supervised gains and improvements over competing Fréchet regression methods in several settings.
ER -