On a 2-relative entropy
arXiv:2112.03582 · doi:10.3390/e24010074
Abstract
We construct a 2-categorical extension of the relative entropy functor of Baez and Fritz, and show that our construction is functorial with respect to vertical morphisms. Moreover, we show such a `2-relative entropy' satisfies natural 2-categorial analogues of convex linearity, vanishing under optimal hypotheses, and lower semicontinuity. While relative entropy is a relative measure of information between probability distributions, we view our construction as a relative measure of information between channels.
arXiv commentNo figures (only diagrams)
References in corpus (7)
- A mathematical theory of resources
- A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
- A Characterization of Entropy in Terms of Information Loss
- Disintegration and Bayesian Inversion via String Diagrams
- A Bayesian Characterization of Relative Entropy
- The information loss of a stochastic map
- A functorial characterization of von Neumann entropy