DeepAI
Log In Sign Up

Deep Deterministic Information Bottleneck with Matrix-based Entropy Functional

01/31/2021
by   Xi Yu, et al.
0

We introduce the matrix-based Renyi's α-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

READ FULL TEXT
04/22/2022

Multi-view Information Bottleneck Without Variational Approximation

By "intelligently" fusing the complementary information across different...
10/12/2021

Gated Information Bottleneck for Generalization in Sequential Environments

Deep neural networks suffer from poor generalization to unseen environme...
10/01/2019

Entropy Penalty: Towards Generalization Beyond the IID Assumption

It has been shown that instead of learning actual object features, deep ...
02/07/2022

Deep Deterministic Independent Component Analysis for Hyperspectral Unmixing

We develop a new neural network based independent component analysis (IC...
09/26/2019

Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks

The aim of this paper is to introduce two widely applicable regularizati...
02/13/2020

The Conditional Entropy Bottleneck

Much of the field of Machine Learning exhibits a prominent set of failur...