Metric Learning in an RKHS

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Tatli, Gokcan, Chen, Yi, Mason, Blake, Nowak, Robert, Vinayak, Ramya Korlakai
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915432153219072
author Tatli, Gokcan
Chen, Yi
Mason, Blake
Nowak, Robert
Vinayak, Ramya Korlakai
author_facet Tatli, Gokcan
Chen, Yi
Mason, Blake
Nowak, Robert
Vinayak, Ramya Korlakai
contents Metric learning from a set of triplet comparisons in the form of "Do you think item h is more similar to item i or item j?", indicating similarity and differences between items, plays a key role in various applications including image retrieval, recommendation systems, and cognitive psychology. The goal is to learn a metric in the RKHS that reflects the comparisons. Nonlinear metric learning using kernel methods and neural networks have shown great empirical promise. While previous works have addressed certain aspects of this problem, there is little or no theoretical understanding of such methods. The exception is the special (linear) case in which the RKHS is the standard Euclidean space $\mathbb{R}^d$; there is a comprehensive theory for metric learning in $\mathbb{R}^d$. This paper develops a general RKHS framework for metric learning and provides novel generalization guarantees and sample complexity bounds. We validate our findings through a set of simulations and experiments on real datasets. Our code is publicly available at https://github.com/RamyaLab/metric-learning-RKHS.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04476
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Metric Learning in an RKHS
Tatli, Gokcan
Chen, Yi
Mason, Blake
Nowak, Robert
Vinayak, Ramya Korlakai
Machine Learning
Artificial Intelligence
Metric learning from a set of triplet comparisons in the form of "Do you think item h is more similar to item i or item j?", indicating similarity and differences between items, plays a key role in various applications including image retrieval, recommendation systems, and cognitive psychology. The goal is to learn a metric in the RKHS that reflects the comparisons. Nonlinear metric learning using kernel methods and neural networks have shown great empirical promise. While previous works have addressed certain aspects of this problem, there is little or no theoretical understanding of such methods. The exception is the special (linear) case in which the RKHS is the standard Euclidean space $\mathbb{R}^d$; there is a comprehensive theory for metric learning in $\mathbb{R}^d$. This paper develops a general RKHS framework for metric learning and provides novel generalization guarantees and sample complexity bounds. We validate our findings through a set of simulations and experiments on real datasets. Our code is publicly available at https://github.com/RamyaLab/metric-learning-RKHS.
title Metric Learning in an RKHS
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2508.04476