Information in Infinite Ensembles of Infinitely-Wide Neural Networks
Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, PMLR 118:1-17, 2020.
In this preliminary work, we study the generalization properties of in nite ensembles of in nitely-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.