References & Citations
Computer Science > Information Theory
Title: A Generalization of Relative Entropy to Count Vectors and its Concentration Property
(Submitted on 24 Apr 2024)
Abstract: We introduce a new generalization of relative entropy to non-negative vectors with sums $\gt 1$. We show in a purely combinatorial setting, with no probabilistic considerations, that in the presence of linear constraints defining a convex polytope, a concentration phenomenon arises for this generalized relative entropy, and we quantify the concentration precisely. We also present a probabilistic formulation, and extend the concentration results to it. In addition, we provide a number of simplifications and improvements to our previous work, notably in dualizing the optimization problem, in the concentration with respect to $\ell_{\infty}$ distance, and in the relationship to generalized KL-divergence. A number of our results apply to general compact convex sets, not necessarily polyhedral.
Submission history
From: Kostas N. Oikonomou [view email][v1] Wed, 24 Apr 2024 13:33:50 GMT (634kb)
Link back to: arXiv, form interface, contact.