Data Entry: Please note that the research database will be replaced by UNIverse by the end of October 2023. Please enter your data into the system https://universe-intern.unibas.ch. Thanks
On the Difference between the Information Bottleneck and the Deep Information Bottleneck
Journal
Entropy
Volume
22
Number
2
Pages / Article-Number
131
Keywords
Markov assumption; Markov chain; conditional independence; deep variational information bottleneck; information bottleneck; mutual information
Abstract
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.