A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 17 of its 26 references that are in the map. First posted on arXiv 18 Jun 2021.
Builds on
17 of 26 references.
References · 17
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2016Understanding deep learning requires rethinking generalizationcited by 1,657
- 2017Exploring Generalization in Deep Learningcited by 595
- 2017Opening the Black Box of Deep Neural Networks via Informationcited by 494
- 2017Information-theoretic analysis of generalization capability of learning algorithmscited by 299
- 2019Uniform convergence may be unable to explain generalization in deep learningcited by 223
- 2018Formal Limitations on the Measurement of Mutual Informationcited by 189
- 2017Generalization in Deep Learningcited by 146
- 2020Reasoning About Generalization via Conditional Mutual Informationcited by 145
- 2019Information-Theoretic Generalization Bounds for SGLD via Data-Dependent Estimatescited by 118
- 2015How much does your data exploration overfit? Controlling bias via information usagecited by 95
5 more
- 2020Sharpened Generalization Bounds based on Conditional Mutual Information and an Application to Noisy, Iterative Algorithmscited by 89
- 2018Generalization Error Bounds for Noisy, Iterative Algorithmscited by 79
- 2018Chaining Mutual Information and Tightening Generalization Boundscited by 65
- 2018An Information-Theoretic View for Deep Learningcited by 5
- 2020A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretabilitycited by 1
Built on by
Citing papers per year: 2022: 1.
1 paper.