Deep Deterministic Information Bottleneck with Matrix-Based Entropy Functional
Xi Yu, Shujian Yu, José C. Prı́ncipe
Abstract
We introduce the matrix-based Rényi’s α-order entropy functional to parameterize Tishby et al. information bottleneck (IB) principle [1] 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.
Topics & Concepts
Information bottleneck methodBottleneckComputer scienceEntropy (arrow of time)Artificial intelligenceAlgorithmMutual informationPhysicsQuantum mechanicsEmbedded systemAdversarial Robustness in Machine LearningNeural Networks and ApplicationsAdvanced Memory and Neural Computing