Skip to content
No description, website, or topics provided.
Jupyter Notebook Stan
Branch: master
Clone or download
Latest commit 766d77a Oct 26, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
HMC-SGD.ipynb Update HMC-SGD.ipynb Oct 26, 2019 Update Oct 26, 2019
alleviating-label-swithchin-poster.pdf adding poster Oct 26, 2019
mixture_all.stan Update mixture_all.stan Oct 26, 2019

Alleviating Label Switching with Optimal Transport


Label switching is a phenomenon arising in mixture model posterior inference that prevents one from meaningfully assessing posterior statistics using standard Monte Carlo procedures. This issue arises due to invariance of the posterior under actions of a group; for example, permuting the ordering of mixture components has no effect on posterior likelihood.

We propose a resolution to label switching that leverages machinery from optimal transport. Our algorithm efficiently computes posterior statistics in the quotient space of the symmetry group. We demonstrate here the performance of our SGD algorithm.


One Jupyter notebook and a Stan code are provided to present our code. The first uses the Stan probabilistic software and therefore requires the Pystan library. The first time this code is used, one should compile the Stan code and record it in a .pkl file (code is provided). For our SGD algorithm, we used the POT library to compute the transport plan.

You can’t perform that action at this time.