https://github.com/brain-research/l2hmc

TensorFlow implementation for training MCMC samplers from the paper: Generalizing Hamiltonian Monte Carlo with Neural Network
https://github.com/brain-research/l2hmc

Last synced: 14 days ago
JSON representation

TensorFlow implementation for training MCMC samplers from the paper: Generalizing Hamiltonian Monte Carlo with Neural Network

• Host: GitHub
• URL: https://github.com/brain-research/l2hmc
• Owner: brain-research
• License: apache-2.0
• Archived: true
• Created: 2017-09-15T20:19:18.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2018-08-14T05:29:04.000Z (about 6 years ago)
• Last Synced: 2024-08-01T16:48:12.709Z (3 months ago)
• Language: Jupyter Notebook
• Homepage:
• Size: 13.9 MB
• Stars: 182
• Watchers: 21
• Forks: 40
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# L2HMC: Automatic Training of MCMC Samplers

TensorFlow open source implementation for training MCMC samplers from the paper:

[*Generalizing Hamiltonian Monte Carlo with Neural Networks*](https://arxiv.org/abs/1711.09268)

by [Daniel Levy](http://ai.stanford.edu/~danilevy), [Matt D. Hoffman](http://matthewdhoffman.com/) and [Jascha Sohl-Dickstein](sohldickstein.com)

---

Given an analytically described distributions (implemented as in `utils/distributions.py`), L2HMC enables training of fast-mixing samplers. We provide an example, in the case of the Strongly-Correlated Gaussian, in the notebook `SCGExperiment.ipynb` --other details are included in the paper.

## Contact

***Code author:*** Daniel Levy

***Pull requests and issues:*** @daniellevy

## Citation

If you use this code, please cite our paper:

```

@article{levy2017generalizing,

  title={Generalizing Hamiltonian Monte Carlo with Neural Networks},

  author={Levy, Daniel and Hoffman, Matthew D. and Sohl-Dickstein, Jascha},

  journal={International Conference on Learning Representations},

  year={2018}

}

```

## Note

This is not an official Google product.