MyJournals Home  

RSS FeedsEntropy, Vol. 22, Pages 131: On the Difference between the Information Bottleneck and the Deep Information Bottleneck (Entropy)

 
 

22 january 2020 13:00:44

 
Entropy, Vol. 22, Pages 131: On the Difference between the Information Bottleneck and the Deep Information Bottleneck (Entropy)
 


Combining the information bottleneck model with deep learning by replacing mutual information terms with deep neural nets has proven successful in areas ranging from generative modelling to interpreting deep neural networks. In this paper, we revisit the deep variational information bottleneck and the assumptions needed for its derivation. The two assumed properties of the data, X and Y, and their latent representation T, take the form of two Markov chains T - X - Y and X - T - Y . Requiring both to hold during the optimisation process can be limiting for the set of potential joint distributions P ( X , Y , T ) . We, therefore, show how to circumvent this limitation by optimising a lower bound for the mutual information between T and Y: I ( T ; Y ) , for which only the latter Markov chain has to be satisfied. The mutual information I ( T ; Y ) can be split into two non-negative parts. The first part is the lower bound for I ( T ; Y ) , which is optimised in deep variational information bottleneck (DVIB) and cognate models in practice. The second part consists of two terms that measure how much the former requirement T - X - Y is violated. Finally, we propose interpreting the family of information bottleneck models as directed graphical models, and show that in this framework, the original and deep information bottlenecks are special cases of a fundamental IB model.


 
217 viewsCategory: Informatics, Physics
 
Entropy, Vol. 22, Pages 132: Electric Double Layers with Surface Charge Regulation Using Density Functional Theory (Entropy)
Entropy, Vol. 22, Pages 137: An Optimization Method of Precision Assembly Process Based on the Relative Entropy Evaluation of the Stress Distribution (Entropy)
 
 
blog comments powered by Disqus


MyJournals.org
The latest issues of all your favorite science journals on one page

Username:
Password:

Register | Retrieve

Search:

Physics


Copyright © 2008 - 2024 Indigonet Services B.V.. Contact: Tim Hulsen. Read here our privacy notice.
Other websites of Indigonet Services B.V.: Nieuws Vacatures News Tweets Nachrichten