Symmetrizing the Kullback-Leibler Distance

347 citations recorded by the source corpus.

How researchers see this paper

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

On Measures of Entropy and Information (2015, background): “Resistor-average entropy [26] The harmonic mean of forward and reversed relative entropies.”
Text Classification Algorithms: A Survey (2019, background): “ximization of the objective function can be re-written as follows: F = å i å j (Vij log((WH) ij) (WH) ij) (31) Information 2019, 10, 150 14 of 68 The objective function, given by the Kullback–Leibler [81,82] divergence, is deﬁned as follows: Hij = Hij å k W kj V kj (WH) kj (32) Wˆ ij = Wij å k V ik ”
How to Explain Individual Classification Decisions (2009, background): “Johnson and Sinanovic (2000). To prevent zero-values in the histograms which would lead to infinite KL distances, an ε > 0 has been added to each bin count.”
No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization (2017, unknown): “Johnson and Sinanović [34] presented simple examples to illustrate that the ordering of the arguments in the K–L divergence might produce substantially different results.”