A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization

Autor:	Lan, Xinjie, Barner, Kenneth
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: To appear in the ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2106.10262 Zobrazit plný text záznamu View this record from Arxiv