Sup-Sums Principles for F-Divergence and a New Definition for t-Entropy

V. I. Bakhtin, A. V. Lebedev
2020 Journal of theoretical probability  
The article presents new $${\sup }$$ sup -sums principles for integral F-divergence for arbitrary convex functions F on the whole real axis and arbitrary (not necessarily positive and normalized) measures. Among applications of these results, we work out a new 'integral' definition for t-entropy explicitly establishing its relation to Kullback–Leibler divergence.
doi:10.1007/s10959-020-01046-5 fatcat:asolki7bevffrhx24txnvkyd44