Information in Infinite Ensembles of Infinitely-Wide Neural Networks

11/20/2019

∙

by   Ravid Schwartz-Ziv, et al.

∙

0

∙

share

In this preliminary work, we study the generalization properties of infinite ensembles of infinitely-wide neural networks. Amazingly, this model family admits tractable calculations for many information-theoretic quantities. We report analytical and empirical investigations in the search for signals that correlate with generalization.