Abstract
On Euclidean spaces, the Gaussian kernel is one of the most widely used kernels in applications. It has also been used on non-Euclidean spaces, where it is known that there may be (and often are) scale parameters for which it is not positive definite. Hope remains that this kernel is positive definite for many choices of parameter. However, we show that the Gaussian kernel is not positive definite on the circle for any choice of parameter. This implies that on metric spaces in which the circle can be isometrically embedded, such as spheres, projective spaces and Grassmannians, the Gaussian kernel is not positive definite for any parameter.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barachant, A., Bonnet, S., Congedo, M., Jutten, C.: Riemannian geometry applied to BCI classification. In: Vigneron, V., Zarzoso, V., Moreau, E., Gribonval, R., Vincent, E. (eds.) LVA/ICA 2010. LNCS, vol. 6365, pp. 629–636. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15995-4_78
Berg, C., Christensen, J.P.R., Ressel, P.: Harmonic Analysis on Semigroups, Graduate Texts in Mathematics, vol. 100. Springer, New York (1984). https://doi.org/10.1007/978-1-4612-1128-0
Borovitskiy, V., Terenin, A., Mostowsky, P., Deisenroth, M.: Matérn Gaussian processes on Riemannian manifolds. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 12426–12437. Curran Associates, Inc. (2020)
Bringmann, K., Folsom, A., Milas, A.: Asymptotic behavior of partial and false theta functions arising from Jacobi forms and regularized characters. J. Math. Phys. 58(1), 011702 (2017). https://doi.org/10.1063/1.4973634
Calinon, S.: Gaussians on Riemannian manifolds: applications for robot learning and adaptive control. IEEE Rob. Autom. Maga. 27(2), 33–45 (2020). https://doi.org/10.1109/MRA.2020.2980548
Carneiro, E., Littmann, F.: Bandlimited approximations to the truncated Gaussian and applications. Constr. Approx. 38(1), 19–57 (2013). https://doi.org/10.1007/s00365-012-9177-8
Cristianini, N., Ricci, E.: Support Vector Machines, pp. 2170–2174. Springer, New York (2016). https://doi.org/10.1007/978-0-387-77242-4
Feragen, A., Hauberg, S.: Open problem: kernel methods on manifolds and metric spaces. What is the probability of a positive definite geodesic exponential kernel? In: Feldman, V., Rakhlin, A., Shamir, O. (eds.) 29th Annual Conference on Learning Theory. Proceedings of Machine Learning Research, vol. 49, pp. 1647–1650. PMLR, Columbia University (2016). https://proceedings.mlr.press/v49/feragen16.html
Feragen, A., Lauze, F., Hauberg, S.: Geodesic exponential kernels: when curvature and linearity conflict. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3032–3042 (2015). https://doi.org/10.1109/CVPR.2015.7298922
Gneiting, T.: Strictly and non-strictly positive definite functions on spheres. Bernoulli 19(4), 1327–1349 (2013). https://doi.org/10.3150/12-BEJSP06
Gonon, L., Grigoryeva, L., Ortega, J.P.: Reservoir kernels and Volterra series. ArXiv Preprint (2022)
Grigoryeva, L., Ortega, J.P.: Dimension reduction in recurrent networks by canonicalization. J. Geom. Mech. 13(4), 647–677 (2021). https://doi.org/10.3934/jgm.2021028
Jaquier, N., Rozo, L.D., Calinon, S., Bürger, M.: Bayesian optimization meets Riemannian manifolds in robot learning. In: Kaelbling, L.P., Kragic, D., Sugiura, K. (eds.) 3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, 30 October–1 November 2019, Proceedings. Proceedings of Machine Learning Research, vol. 100, pp. 233–246. PMLR (2019). http://proceedings.mlr.press/v100/jaquier20a.html
Jayasumana, S., Hartley, R., Salzmann, M., Li, H., Harandi, M.: Kernel methods on Riemannian manifolds with Gaussian RBF kernels. IEEE Trans. Pattern Anal. Mach. Intell. 37(12), 2464–2477 (2015). https://doi.org/10.1109/TPAMI.2015.2414422
Romeny, B.M.H.: Geometry-Driven Diffusion in Computer Vision. Springer, Heidelberg (2013). google-Books-ID: Fr2rCAAAQBAJ
Salvi, C., Cass, T., Foster, J., Lyons, T., Yang, W.: The Signature Kernel is the solution of a Goursat PDE. SIAM J. Math. Data Sci. 3(3), 873–899 (2021)
Schoenberg, I.J.: Metric spaces and positive definite functions. Trans. Am. Math. Soc. 44(3), 522–536 (1938). http://www.jstor.org/stable/1989894
Schölkopf, B., Smola, A., Müller, K.R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput. 10(5), 1299–1319 (1998). https://doi.org/10.1162/089976698300017467
Sra, S.: Positive definite matrices and the S-divergence. Proc. Am. Math. Soc. 144(7), 2787–2797 (2016). https://www.jstor.org/stable/procamermathsoci.144.7.2787
Wood, A.T.A.: When is a truncated covariance function on the line a covariance function on the circle? Stat. Prob. Lett. 24(2), 157–164 (1995). https://doi.org/10.1016/0167-7152(94)00162-2
Ye, K., Lim, L.H.: Schubert varieties and distances between subspaces of different dimensions. SIAM J. Matrix Anal. Appl. 37(3), 1176–1197 (2016). https://doi.org/10.1137/15M1054201
Zhu, P., Knyazev, A.: Angles between subspaces and their tangents. J. Numer. Math. 21(4), 325–340 (2013). https://doi.org/10.1515/jnum-2013-0013
Acknowledgments
The authors acknowledge financial support from the School of Physical and Mathematical Sciences and the Presidential Postdoctoral Fellowship programme at Nanyang Technological University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Da Costa, N., Mostajeran, C., Ortega, JP. (2023). The Gaussian Kernel on the Circle and Spaces that Admit Isometric Embeddings of the Circle. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2023. Lecture Notes in Computer Science, vol 14071. Springer, Cham. https://doi.org/10.1007/978-3-031-38271-0_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-38271-0_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38270-3
Online ISBN: 978-3-031-38271-0
eBook Packages: Computer ScienceComputer Science (R0)