Abstract
This work studies a parametrized family of symmetric divergences on the set of Hermitian positive definite matrices which are defined using the \(\alpha \)-Tsallis entropy \(\forall \alpha \in \mathbb {R}\). This family unifies in particular the Quantum Jensen-Shannon divergence, defined using the von Neumann entropy, and the Jensen-Bregman Log-Det divergence. The divergences, along with their metric properties, are then generalized to the setting of positive definite trace class operators on an infinite-dimensional Hilbert space \(\forall \alpha \in \mathbb {R}\). In the setting of reproducing kernel Hilbert space (RKHS) covariance operators, all divergences admit closed form formulas in terms of the corresponding kernel Gram matrices.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bai, L., Rossi, L., Torsello, A., Hancock, E.R.: A quantum Jensen-Shannon graph kernel for unattributed graphs. Pattern Recogn. 48(2), 344–355 (2015)
Briët, J., Harremoës, P.: Properties of classical and quantum Jensen-Shannon divergence. Phys. Rev. A 79(5), 052311 (2009)
Carlen, E.: Trace inequalities and quantum entropy: an introductory course. Entropy Quant. 529, 73–140 (2010)
Cherian, A., Sra, S., Banerjee, A., Papanikolopoulos, N.: Jensen-Bregman logdet divergence with application to efficient similarity search for covariance matrices. TPAMI 35(9), 2161–2174 (2012)
Congedo, M., Barachant, A., Bhatia, R.: Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review. Brain Comput. Interfaces 4(3), 155–174 (2017)
Dajka, J., Luczka, J., Hänggi, P.: Distance between quantum states in the presence of initial qubit-environment correlations: a comparative study. Phys. Rev. A 84(3), 032120 (2011)
De Domenico, M., Nicosia, V., Arenas, A., Latora, V.: Structural reducibility of multilayer networks. Nat. Commun. 6(1), 1–9 (2015)
Dryden, I., Koloydenko, A., Zhou, D.: Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging. Ann. Appl. Stat. 3, 1102–1123 (2009)
Harandi, M., Salzmann, M., Porikli, F.: Bregman divergences for infinite dimensional covariance matrices. In: CVPR (2014)
Lamberti, P., Majtey, A., Borras, A., Casas, M., Plastino, A.: Metric character of the quantum Jensen-Shannon divergence. Phys. Rev. A 77(5), 052311 (2008)
Minh, H.Q.: Alpha-Beta Log-Determinant divergences between positive definite trace class operators. Inf. Geom. 2(2), 101–176 (2019)
Minh, H.: Infinite-dimensional Log-Determinant divergences between positive definite trace class operators. Linear Algebra Appl. 528, 331–383 (2017)
Minh, H., Murino, V.: Covariances in computer vision and machine learning. Synth. Lect. Comput. Vis. 7(4), 1–170 (2017)
Nielsen, F., Boltz, S.: The Burbea-Rao and Bhattacharyya centroids. IEEE Trans. Inf. Theor. 57(8), 5455–5466 (2011)
Nock, R., Magdalou, B., Briys, E., Nielsen, F.: Mining matrix data with Bregman matrix divergences for portfolio selection. In: Nielsen, F., Bhatia, R. (eds.) Matrix Information Geometry, pp. 373–402. Springer, Berlin, Heidelberg (2013). https://doi.org/10.1007/978-3-642-30232-9_15
Rossi, L., Torsello, A., Hancock, E.R., Wilson, R.C.: Characterizing graph symmetries through quantum Jensen-Shannon divergence. Physi. Rev. E 88(3), 032806 (2013)
Sra, S.: Positive definite matrices and the S-divergence. Proc. Am. Math. Soc. 144(7), 2787–2797 (2016)
Sra, S.: Metrics induced by Jensen-Shannon and related divergences on positive definite matrices. Linear Algebra Appl. 616, 125–138 (2021)
Steinwart, I., Christmann, A.: Support Vector Machines. Springer Science & Business Media, London (2008)
Virosztek, D.: The metric property of the quantum Jensen-Shannon divergence. Adv. Math. 380, 107595 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Minh, H.Q. (2021). Quantum Jensen-Shannon Divergences Between Infinite-Dimensional Positive Definite Operators. In: Nielsen, F., Barbaresco, F. (eds) Geometric Science of Information. GSI 2021. Lecture Notes in Computer Science(), vol 12829. Springer, Cham. https://doi.org/10.1007/978-3-030-80209-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-80209-7_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80208-0
Online ISBN: 978-3-030-80209-7
eBook Packages: Computer ScienceComputer Science (R0)