Maximal information divergence from statistical models defined by neural networks

We review recent results about the maximal values of the Kullback-Leibler information divergence from statistical models defined by neural networks, including naïve Bayes models, restricted Boltzmann machines, deep belief networks, and various classes of exponential families. We illustrate approaches to compute the maximal divergence from a given model starting from simple sub- or super-models. We give a new result for deep and narrow belief networks with finite-valued units.

Subjects

exponential family

Kullback-Leibler divergence

multi-information

neural network

DDC Class

004: Informatik

Options

Maximal information divergence from statistical models defined by neural networks