Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional

arXiv2102.00533MaRDI QIDQ6359496

Author name not available (Why is that?)

Publication date: 31 January 2021

Abstract: We introduce the matrix-based Renyi's $alpha$-order entropy functional to parameterize Tishby et al. information bottleneck (IB) principle with a neural network. We term our methodology Deep Deterministic Information Bottleneck (DIB), as it avoids variational inference and distribution assumption. We show that deep neural networks trained with DIB outperform the variational objective counterpart and those that are trained with other forms of regularization, in terms of generalization performance and robustness to adversarial attack.Code available at https://github.com/yuxi120407/DIB

Has companion code repository: https://github.com/yuxi120407/DIB

This page was built for publication: Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6359496)