Variational Predictive Information Bottleneck

10/23/2019

∙

by   Alexander A. Alemi, et al.

∙

0

∙

share

In classic papers, Zellner demonstrated that Bayesian inference could be derived as the solution to an information theoretic functional. Below we derive a generalized form of this functional as a variational lower bound of a predictive information bottleneck objective. This generalized functional encompasses most modern inference procedures and suggests novel ones.