Metrics Induced by Jensen-Shannon and Related Divergences on Positive Definite Matrices

We study metric properties of symmetric divergences on Hermitian positive definite matrices. In particular, we prove that the square root of these divergences is a distance metric. As a corollary we obtain a proof of the metric property for Quantum Jensen-Shannon-(Tsallis) divergences (parameterized by $\alpha\in [0,2]$), which in turn (for $\alpha=1$) yields a proof of the metric property of the Quantum Jensen-Shannon divergence that was conjectured by Lamberti \emph{et al.} a decade ago (\emph{Metric character of the quantum Jensen-Shannon divergence}, Phy.\ Rev.\ A, \textbf{79}, (2008).) A somewhat more intricate argument also establishes metric properties of Jensen-R\'enyi divergences (for $\alpha \in (0,1)$), and outlines a technique that may be of independent interest.

[1]  F. Yger,et al.  Riemannian Approaches in Brain-Computer Interfaces: A Review , 2017, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  Jerzy Dajka,et al.  Distance between quantum states in the presence of initial qubit-environment correlations: A comparative study , 2011, 1107.1732.

[3]  D'aniel Virosztek The metric property of the quantum Jensen-Shannon divergence , 2019, 1910.10447.

[4]  A. Plastino,et al.  Metric character of the quantum Jensen-Shannon divergence , 2008, 0801.1586.

[5]  Inderjit S. Dhillon,et al.  Clustering with Bregman Divergences , 2005, J. Mach. Learn. Res..

[6]  Mehrtash Harandi,et al.  Dimensionality Reduction on SPD Manifolds: The Emergence of Geometry-Aware Methods , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[8]  Serge Fehr,et al.  On quantum Rényi entropies: A new generalization and some properties , 2013, 1306.3142.

[9]  Inderjit S. Dhillon,et al.  Low-Rank Kernel Learning with Bregman Matrix Divergences , 2009, J. Mach. Learn. Res..

[10]  S. Sra On the matrix square root via geometric optimization , 2015, 1507.08366.

[11]  T. Raghavan,et al.  Nonnegative Matrices and Applications , 1997 .

[12]  D. Petz Quasi-entropies for finite quantum systems , 1986 .

[13]  Anoop Cherian,et al.  Jensen-Bregman LogDet Divergence with Application to Efficient Similarity Search for Covariance Matrices , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Suvrit Sra,et al.  Conic Geometric Optimization on the Manifold of Positive Definite Matrices , 2013, SIAM J. Optim..

[15]  C. R. Rao,et al.  Entropy differential metric, distance and divergence measures in probability spaces: A unified approach , 1982 .

[16]  Frank Nielsen,et al.  The Burbea-Rao and Bhattacharyya Centroids , 2010, IEEE Transactions on Information Theory.

[17]  C. R. Rao,et al.  On the convexity of some divergence measures based on entropy functions , 1982, IEEE Trans. Inf. Theory.

[18]  I. Chuang,et al.  Quantum Computation and Quantum Information: Bibliography , 2010 .

[19]  R. Bhatia Positive Definite Matrices , 2007 .

[20]  S. Sra Positive definite matrices and the S-divergence , 2011, 1110.1773.

[21]  W. Donoghue Monotone Matrix Functions and Analytic Continuation , 1974 .

[22]  Peter Harremoës,et al.  Properties of Classical and Quantum Jensen-Shannon Divergence , 2009 .

[23]  Flemming Topsøe,et al.  Jensen-Shannon divergence and Hilbert space embedding , 2004, International Symposium onInformation Theory, 2004. ISIT 2004. Proceedings..

[24]  Suvrit Sra,et al.  Logarithmic inequalities under a symmetric polynomial dominance order , 2017, Proceedings of the American Mathematical Society.

[25]  Richard C. Wilson,et al.  Characterizing graph symmetries through quantum Jensen-Shannon divergence. , 2013, Physical review. E, Statistical, nonlinear, and soft matter physics.