Bottleneck Conditional Density Estimation (ICML 2017)
Switch branches/tags
Nothing to show
Clone or download
Latest commit f5fc70f Jul 6, 2017
Type Name Latest commit message Commit time
Failed to load latest commit information.
.gitignore First commit Jun 30, 2017
LICENSE Initial commit Jun 29, 2017 Add dependency version info Jul 7, 2017 First commit Jun 30, 2017 First commit Jun 30, 2017 First commit Jun 30, 2017 Remove naming of loss tensor op Jun 30, 2017 Change assert to warning Jun 30, 2017 Simplify sanity checks Jun 30, 2017 First commit Jun 30, 2017


The Bottleneck Conditional Density Estimator provides a semi-supervised learning framework for high-dimensional conditional density estimation. This repository provides code to run experiments in from the 2017 ICML paper Bottleneck Conditional Density Estimation.

This work was done while interning at Adobe Systems.


Please make sure to pip install the following dependencies



To run the model (2-layer hybrid+factored BCDE), simply do:

python --model hybrid_factored