Jensen-Shannon divergence and Hilbert space embedding

By Bent Fuglede, Flemming Topsøe. 2004

796 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

In Statistics and Probability

Citations in the corpus

Testing Hypotheses by Regularized Maximum Mean Discrepancy (2013, neutral): “The modified Jensen-Shanon divergence (JS) [3] corresponding to RMMD is defined as:”
Hilbert Space Embeddings and Metrics on Probability Measures (2009, background): “Broadly, this relates to the work on Hilbertian metrics and positive definite kernels on probability measures by Hein and Bousquet (2005) and Fuglede and Topsøe (2003).”
On integral probability metrics, φ-divergences and binary classification (2009, background): “wn to be metrics on P0, for example, the square root of variational distance, the square root of Hellinger’s distance, the square root of Jensen-Shannon divergence etc., are shown to be metrics on P0 [8, 11, 17]. Similarly, [23, Theorem 1] has shown that certain powers of Dφ is a metric on P0. So, o”
Forecasting of density functions with an application to cross-sectional and intraday returns (2019, methodology): “We make the JSD a metric between any two probability densities by taking its square root (see e.g. Fuglede & Topsøe, 2004).”
AdaGAN: Boosting Generative Models (2017, methodology): “As demonstrated in [16, 17], several commonly used symmetric f -divergences are Hilbertian metrics, which in particular means that their square root satisfies the triangle inequality.”
Integrative annotation of human large intergenic noncoding RNAs reveals global properties and specific subclasses. (2011, methodology): “Relying on the theorem that the square root of the JS divergence is a metric (Fuglede and Topsoe 2004), we define the distance Cabili et al.”
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals (2021, neutral): “where D J S (·, ·) is the Jensen-Shannon divergence [8], which measures the difference between two distributions in a symmetric way.”
Deep Graph Clustering via Dual Correlation Reduction (2021, background): “where JSD(·) refers to the Jensen-Shannon divergence (Fuglede and Topsoe 2004).”
Semigroup Kernels on Measures (2005, methodology): “…f , f ) def = h( f + f 2 ) − h( f ) + h( f ) 2 , (2) known as the Jensen divergence (or Jensen-Shannon divergence) between f and f , which as noted by Fuglede and Topsøe (2004) can be seen as a symmetrized version of the Kullback-Leibler (KL) divergence D, since J( f , f ) = 1 2 D( f || f + f 2 )…”
Generalized Clustering via Kernel Embeddings (2009, positive): “For a mixture P = π1P1+π2P2, the latter isDJS(P1, P2) = π1DKL(P1, P )+π2DKL(P2, P ) (Fuglede and Topsøe, 2004).”
Properties of Classical and Quantum Jensen-Shannon Divergence (2008, methodology): “[47] B. Fuglede and F. Topsøe.”