A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization
arXiv:2106.10262
Abstract
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.
arXiv commentTo appear in the ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Opening the Black Box of Deep Neural Networks via Information
- Uniform convergence may be unable to explain generalization in deep learning
- Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimates
- How much does your data exploration overfit? Controlling bias via information usage
- An Information-Theoretic View for Deep Learning
- Reasoning About Generalization via Conditional Mutual Information
- A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretability