https://github.com/leoduan/TransportMonteCarlo

https://github.com/leoduan/TransportMonteCarlo

Last synced: 14 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/leoduan/TransportMonteCarlo
• Owner: leoduan
• Created: 2019-08-20T14:05:54.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2020-07-30T17:42:27.000Z (over 4 years ago)
• Last Synced: 2024-08-01T16:48:04.927Z (3 months ago)
• Language: Jupyter Notebook
• Size: 1.22 MB
• Stars: 8
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Transport Monte Carlo

Example code for using Transport Monte Carlo --- using random transport plan and optimization to rapidly estimate the posterior distribution

1. Sampling from a Normal Mixture:

https://nbviewer.jupyter.org/github/leoduan/TransportMonteCarlo/blob/master/gaussianMixtureTMC.ipynb

2. Sampling from a multi-modal distribution (Liang 2005):

https://nbviewer.jupyter.org/github/leoduan/TransportMonteCarlo/blob/master/MultimodalTMC.ipynb

3. High-dimensional regression using the regularized horseshoe prior (Piironen and Vehtari 2017) :

https://nbviewer.jupyter.org/github/leoduan/TransportMonteCarlo/blob/master/regularizedHorseshoe.ipynb

4. Binary adjacency matrix estimation under degree regularization:

https://github.com/leoduan/TransportMonteCarlo/blob/master/edgeSamplingUnderDegreeReg.ipynb

For other target distribution, simply modify the log-prior-likelihood function.

For reference, see

Leo L. Duan. Transport Monte Carlo 2019+. http://arxiv.org/abs/1907.10448