Properties of Classical and Quantum Jensen-Shannon Divergence
By J. Briet, Peter Harremoës. 2008
145 citations recorded by the source corpus.
Jensen-Shannon divergence (JD) is a symmetrized and smoothed version of the most important divergence measure of information theory, Kullback divergence. As opposed to Kullback divergence it determines in a very direct way a metric; indeed, it is the square of a metric. We consider a family of divergence measures (JDα for α > 0), the Jensen divergences of order α, which generalize JD as JD1 = JD. Using a result of Schoenberg, we prove that JDα is the square of a metric for α ∈ (0, 2] , and that the resulting metric space of probability distributions can be isometrically embedded in a real Hilbert space. Quantum Jensen-Shannon divergence (QJD) is a symmetrized and smoothed version of quantum relative entropy and can be extended to a family of quantum Jensen divergences of order α (QJDα). We strengthen results by Lamberti et al. by proving that for qubits and pure states, QJD α is a metric space which can be isometrically embedded in a real Hilbert space when α ∈ (0, 2] . In analogy with Burbea and Rao’s generalization of JD, we also define general QJD by associating a Jensen-type quantity to any weighted family of states. Appropriate interpretations of quantities introduced are discussed and bounds are derived in terms of the total variation and trace distance.
Subfields: Applied Mathematics, Artificial Intelligence, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/3172efd0a0d2d2d2428652846e4f4ac70d9af3e1
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Applied Mathematics
In Artificial Intelligence
In Statistical and Nonlinear Physics
- M. A. Porter
- Manlio De Domenico
- Alex Arenas
- Ingemar Bengtsson
- Karol Zyczkowski
- Santo Fortunato
- Olaf Sporns
- Mark Newman
Citations in the corpus
- Linear Algebra and its Applications (2010, unknown): “So we require The number of iterations k i , i = 1,2, is now chosen as follows.”
- Multilayer Analysis and Visualization of Networks (2014, background): “By definition, the quantum Jensen–Shannon divergence is symmetric and its square root, which is usually called the Jensen–Shannon distance, satisfies the properties of a metric [49].”
- Geometry of Quantum States: Index (2007, background): “2 This was shown in 2003 by Endres and Schindelin [295], and the result is expected to generalise to the quantum case [175, 570].”