activity
20182020
most citedOn the Difference Between the Information Bottleneck and the Deep Information Bottleneck

10 citations · 10 across the 1 of their papers we have counts for

collaborators

5 papers

cs.LG2020

Inverse Learning of Symmetries

Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek +1

Symmetry transformations induce invariances which are frequently described with deep latent variable models. In many complex domains, such as the chemical space, invariances can be…

cs.LG201910 cited

On the Difference Between the Information Bottleneck and the Deep Information Bottleneck

Aleksander Wieczorek, Volker Roth

Combining the Information Bottleneck model with deep learning by replacing mutual information terms with deep neural nets has proved successful in areas ranging from generative mod…

cs.CV2018

Informed MCMC with Bayesian Neural Networks for Facial Image Analysis

Adam Kortylewski, Mario Wieser, Andreas Morel-Forster +4

Computer vision tasks are difficult because of the large variability in the data that is induced by changes in light, background, partial occlusion as well as the varying pose, tex…

stat.ML2018

Cause-Effect Deep Information Bottleneck For Systematically Missing Covariates

Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek +1

Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding. The task is often complicated by the fact…

stat.ML2018

Learning Sparse Latent Representations with the Deep Copula Information Bottleneck

Aleksander Wieczorek, Mario Wieser, Damian Murezzan +1

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 m…