Stochastic Gradient MCMC for Time Series SSMs

This repo will contain the python code for our "SGMCMC for Time Series SSMs" paper (link).

Source code is in the code/sgmcmc_ssm folder. Scripts/Jupyter Notebooks for experiments will be in the experiments folder.

Installation

Add the code/sgmcmc_ssm folder to the PYTHONPATH.

Requirements: Python 3+, numpy, pandas, scipy, seaborn, joblib, scikit-learn,

Usage Example

Under construction

See code/README.md

Synthetic LGSSM Script Example

cd code/
ipython demo/lgssm_demo.py

Development Setup

Under construction

Meta

Christopher Aicher – [email protected]

Distributed under the MIT license. See LICENSE for more information.

https://github.com/aicherc/sgmcmc_ssm_code

Contributing

1. Fork it (https://github.com/aicherc/sgmcmc_ssm_code/fork)
2. Create your feature branch (git checkout -b feature/fooBar)
3. Commit your changes (git commit -am 'Add some fooBar')
4. Push to the branch (git push origin feature/fooBar)
5. Create a new Pull Request