Recently, Mutual Information (MI) has attracted attention in bounding the generalization error of Deep Neural Networks (DNNs). However, it is intractable to accurately estimate the MI in DNNs, thus most previous works have to relax the MI bound, which in turn weakens the information theoretic explanation for generalization. To address the limitation, this paper introduces a probabilistic representation of DNNs for accurately estimating the MI. Leveraging the proposed MI estimator, we validate the information theoretic explanation for generalization, and derive a tighter generalization bound than the state-of-the-art relaxations.
@article{arxiv.2106.10262,
title = {A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization},
author = {Xinjie Lan and Kenneth Barner},
journal= {arXiv preprint arXiv:2106.10262},
year = {2021}
}
Comments
To appear in the ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI