Geiger Bernhard
2018
This short note presents results about the symmetric Jensen-Shannon divergence between two discrete mixture distributions p1 and p2. Specifically, for i=1,2, pi is the mixture of a common distribution q and a distribution p̃ i with mixture proportion λi. In general, p̃ 1≠p̃ 2 and λ1≠λ2. We provide experimental and theoretical insight to the behavior of the symmetric Jensen-Shannon divergence between p1 and p2 as the mixture proportions or the divergence between p̃ 1 and p̃ 2 change. We also provide insight into scenarios where the supports of the distributions p̃ 1, p̃ 2, and q do not coincide.
Geiger Bernhard
2018
The Global Benefits of Open Research and How It Can Change Scientific Publishing
Martyn Rittman MDPI
This entry for the 2018 MDPI English Writing Prize has been published as a chapter of "The Global Benefits of Open Research", edited by Martyn Rittman.