Variational Information Bottleneck for Semi-Supervised Classification

Variational Information Bottleneck for Semi-Supervised Classification

In this paper, we consider an information bottleneck (IB) framework for semi-supervised classification with several families of priors on latent space representation. We apply a variational decomposition of mutual information terms of IB. Using this decomposition we perform an analysis of several re...

Full description

Bibliographic Details
Main Authors: Slava Voloshynovskiy, Olga Taran, Mouad Kondah, Taras Holotyak, Danilo Rezende
Format: Article
Language:English
Published: MDPI AG 2020-08-01
Series:Entropy
Subjects:
information bottleneck principle
deep networks
semi-supervised classification
latent space representation
hand crafted priors
learnable priors
Online Access:https://www.mdpi.com/1099-4300/22/9/943

Internet

https://www.mdpi.com/1099-4300/22/9/943

Similar Items