edoc

Learning Sparse Latent Representations with the Deep Copula Information Bottleneck

Wieser, Mario and Wieczorek, Aleksander and Murezzan, Damian and Roth, Volker. (2018) Learning Sparse Latent Representations with the Deep Copula Information Bottleneck. In: International Conference on Learning Representations.

[img] PDF
Restricted to Repository staff only

3171Kb

Official URL: https://edoc.unibas.ch/69174/

Downloads: Statistics Overview

Abstract

Deep latent variable models are powerful tools for representation learning. In this paper, we adopt the deep information bottleneck model, identify its shortcomings and propose a model that circumvents them. To this end, we apply a copula transformation which, by restoring the invariance properties of the information bottleneck method, leads to disentanglement of the features in the latent space. Building on that, we show how this transformation translates to sparsity of the latent space in the new model. We evaluate our method on artificial and real data.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Datenanalyse (Roth)
UniBasel Contributors:Roth, Volker and Wieser, Mario and Wieczorek, Aleksander and Murezzan, Damian
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:ICLR
Note:Publication type according to Uni Basel Research Database: Conference paper
Language:English
Related URLs:
Last Modified:08 Mar 2019 14:40
Deposited On:08 Mar 2019 14:38

Repository Staff Only: item control page