Saved in:
Bibliographic Details
Main Authors: Feito-Casares, Enrique, Melgarejo-Meseguer, Francisco M., Rojo-Álvarez, José-Luis
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.05811
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910193577623552
author Feito-Casares, Enrique
Melgarejo-Meseguer, Francisco M.
Rojo-Álvarez, José-Luis
author_facet Feito-Casares, Enrique
Melgarejo-Meseguer, Francisco M.
Rojo-Álvarez, José-Luis
contents Motivated by the growing interest in representation learning approaches that uncover the latent structure of high-dimensional data, this work proposes new algorithms for reconstruction-based manifold learning within Reproducing-Kernel Hilbert Spaces (RKHS). Each observation is first reconstructed as a linear combination of the other samples in the RKHS, by optimizing a vector form of the Representer Theorem for their autorepresentation property. A separable operator-valued kernel extends the formulation to vector-valued data while retaining the simplicity of a single scalar similarity function. A subsequent kernel-alignment task projects the data into a lower-dimensional latent space whose Gram matrix aims to match the high-dimensional reconstruction kernel, thus transferring the auto-reconstruction geometry of the RKHS to the embedding. Therefore, the proposed algorithms represent an extended approach to the autorepresentation property, exhibited by many natural data, by using and adapting well-known results of Kernel Learning Theory. Numerical experiments on both simulated (concentric circles and swiss-roll) and real (cancer molecular activity and IoT network intrusions) datasets provide empirical evidence of the practical effectiveness of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2601_05811
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning Reconstructive Embeddings in Reproducing Kernel Hilbert Spaces via the Representer Theorem
Feito-Casares, Enrique
Melgarejo-Meseguer, Francisco M.
Rojo-Álvarez, José-Luis
Machine Learning
Artificial Intelligence
Motivated by the growing interest in representation learning approaches that uncover the latent structure of high-dimensional data, this work proposes new algorithms for reconstruction-based manifold learning within Reproducing-Kernel Hilbert Spaces (RKHS). Each observation is first reconstructed as a linear combination of the other samples in the RKHS, by optimizing a vector form of the Representer Theorem for their autorepresentation property. A separable operator-valued kernel extends the formulation to vector-valued data while retaining the simplicity of a single scalar similarity function. A subsequent kernel-alignment task projects the data into a lower-dimensional latent space whose Gram matrix aims to match the high-dimensional reconstruction kernel, thus transferring the auto-reconstruction geometry of the RKHS to the embedding. Therefore, the proposed algorithms represent an extended approach to the autorepresentation property, exhibited by many natural data, by using and adapting well-known results of Kernel Learning Theory. Numerical experiments on both simulated (concentric circles and swiss-roll) and real (cancer molecular activity and IoT network intrusions) datasets provide empirical evidence of the practical effectiveness of the proposed approach.
title Learning Reconstructive Embeddings in Reproducing Kernel Hilbert Spaces via the Representer Theorem
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2601.05811