Learning Reconstructive Embeddings in Reproducing Kernel Hilbert Spaces via the Representer Theorem

ArXi:2601.05811v1 Announce Type: cross 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.