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.
@article{arxiv.1911.09189,
title = {Information in Infinite Ensembles of Infinitely-Wide Neural Networks},
author = {Ravid Shwartz-Ziv and Alexander A. Alemi},
journal= {arXiv preprint arXiv:1911.09189},
year = {2022}
}
Comments
2nd Symposium on Advances in Approximate Bayesian Inference, 2019