A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization
This work addresses a fundamental limitation in understanding generalization in deep learning, though it appears incremental as it builds on existing mutual information frameworks.
The paper tackles the problem of intractable mutual information estimation in deep neural networks by introducing a probabilistic representation, enabling a tighter generalization bound that validates information-theoretic explanations for generalization.
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.