Maximal Information Divergence from Statistical Models defined by Neural Networks
This work addresses theoretical bounds on model divergence for researchers in machine learning and statistics, but it is incremental as it builds on existing review and computational approaches.
The paper reviews and computes maximal Kullback-Leibler divergence values for neural network-based statistical models, presenting a new result for deep, narrow belief networks with finite-valued units.
We review recent results about the maximal values of the Kullback-Leibler information divergence from statistical models defined by neural networks, including naive 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.