The optimal assignment kernel is not positive definite
Machine Learning
2008-01-29 v1
Authors:
Jean-Philippe Vert
Abstract
We prove that the optimal assignment kernel, proposed recently as an attempt to embed labeled graphs and more generally tuples of basic data to a Hilbert space, is in fact not always positive definite.
Cite
@article{arxiv.0801.4061,
title = {The optimal assignment kernel is not positive definite},
author = {Jean-Philippe Vert},
journal= {arXiv preprint arXiv:0801.4061},
year = {2008}
}
Related papers
View all related →
Machine Learning · Computer Science
On Valid Optimal Assignment Kernels and Applications to Graph Classification
Nils M. Kriege, Pierre-Louis Giscard, Richard C. Wilson
2017-02-01
Machine Learning · Statistics
Positive Definite Kernels in Machine Learning
Marco Cuturi
2009-12-04
Functional Analysis · Mathematics
New characterizations of reproducing kernel Hilbert spaces and applications to metric geometry
Daniel Alpay, Palle Jorgensen
2020-11-20
Computer Vision and Pattern Recognition · Computer Science
Expanding the Family of Grassmannian Kernels: An Embedding Perspective
Mehrtash T. Harandi, Mathieu Salzmann, Sadeep Jayasumana, Richard Hartley +1
2014-07-07
Machine Learning · Statistics
A Kernel for Hierarchical Parameter Spaces
Frank Hutter, Michael A. Osborne
2013-10-23
Methodology · Statistics
The Alpha-Beta-Symetric Divergence and their Positive Definite Kernel
Mactar Ndaw, Macoumba Ndour, Papa Ngom
2018-09-18
Functional Analysis · Mathematics
Nonuniform sampling, reproducing kernels, and the associated Hilbert spaces
Palle Jorgensen, Feng Tian
2016-01-28
Functional Analysis · Mathematics
Positive Hankel operators, positive definite kernels and related topics
Piotr Niemiec
2020-09-07
Machine Learning · Statistics
Characteristic kernels on Hilbert spaces, Banach spaces, and on sets of measures
Johanna Ziegel, David Ginsbourger, Lutz Dümbgen
2022-06-16
Machine Learning · Computer Science
Conditional mean embeddings and optimal feature selection via positive definite kernels
Palle E. T. Jorgensen, Myung-Sin Song, James Tian
2023-05-16
Neurons and Cognition · Quantitative Biology
Kernel methods on spike train space for neuroscience: a tutorial
Il Memming Park, Sohan Seth, Antonio R. C. Paiva, Lin Li +1
2013-10-16
Operator Algebras · Mathematics
Noncommutative reproducing kernel Hilbert spaces
Joseph A. Ball, Gregory Marx, Victor Vinnikov
2016-02-03
Functional Analysis · Mathematics
On the extension of positive definite kernels to topological algebras
Daniel Alpay, Ismael L. Paiva
2024-01-05
Statistics Theory · Mathematics
Kernel methods in machine learning
Thomas Hofmann, Bernhard Schölkopf, Alexander J. Smola
2009-09-29
Machine Learning · Computer Science
Notes on Kernel Methods in Machine Learning
Diego Armando Pérez-Rosero, Danna Valentina Salazar-Dubois, Juan Camilo Lugo-Rojas, Andrés Marino Álvarez-Meza +1
2025-11-19
Machine Learning · Statistics
Prior shift estimation for positive unlabeled data through the lens of kernel embedding
Jan Mielniczuk, Wojciech Rejchel, Paweł Teisseyre
2026-05-22
Functional Analysis · Mathematics
Universal Kernel Models for Iterated Completely Positive Maps
James Tian
2025-11-18
Computer Vision and Pattern Recognition · Computer Science
A Framework for Shape Analysis via Hilbert Space Embedding
Sadeep Jayasumana, Mathieu Salzmann, Hongdong Li, Mehrtash Harandi
2014-12-16
Functional Analysis · Mathematics
Sampling with positive definite kernels and an associated dichotomy
Palle Jorgensen, Feng Tian
2017-08-22
Numerical Analysis · Mathematics
Approximation with Conditionally Positive Definite Kernels on Deficient Sets
Oleg Davydov
2025-08-26
Quantum Physics · Physics
Experimental kernel-based quantum machine learning in finite feature space
Karol Bartkiewicz, Clemens Gneiting, Antonín Černoch, Kateřina Jiráková +2
2022-06-15
Complex Variables · Mathematics
Optimal approximants and orthogonal polynomials in several variables
Meredith Sargent, Alan Sola
2022-05-03
Optimization and Control · Mathematics
Positive semidefinite approximations to the cone of copositive kernels
Olga Kuryatnikova, Juan C. Vera
2018-12-04
Functional Analysis · Mathematics
Metric duality between positive definite kernels and boundary processes
Palle Jorgensen, Feng Tian
2017-06-30
Operator Algebras · Mathematics
Operator-Valued Kernels, Machine Learning, and Dynamical Systems
Palle E. T. Jorgensen, James Tian
2024-10-14