https://github.com/AdamCobb/hamiltorch

PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks
https://github.com/AdamCobb/hamiltorch

bnn hmc pytorch

Last synced: about 1 month ago
JSON representation

PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks

• Host: GitHub
• URL: https://github.com/AdamCobb/hamiltorch
• Owner: AdamCobb
• License: bsd-2-clause
• Created: 2019-10-04T11:23:42.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2023-11-14T15:05:37.000Z (8 months ago)
• Last Synced: 2024-02-10T16:39:41.670Z (5 months ago)
• Topics: bnn, hmc, pytorch
• Language: Jupyter Notebook
• Homepage:
• Size: 3.26 MB
• Stars: 369
• Watchers: 14
• Forks: 57
• Open Issues: 11
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Lists

• awesome-sciml - AdamCobb/hamiltorch: PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks
• awesome-stars - AdamCobb/hamiltorch - PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks (Jupyter Notebook)

README

        
# hamiltorch [![Build Status](https://travis-ci.com/AdamCobb/hamiltorch.svg?token=qJKqovbtw9EzCw99Nvg8&branch=master)](https://travis-ci.com/AdamCobb/hamiltorch)

 PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks

 * Perform HMC in user-defined log probabilities and in PyTorch neural networks (objects inheriting from the `torch.nn.Module`).

 * Available sampling schemes:

     * HMC

     * No-U-Turn Sampler (currently adapts step-size only)

     * Implicit RMHMC

     * Explicit RMHMC

     * Symmetric Split HMC

 ## How to install

```

pip install git+https://github.com/AdamCobb/hamiltorch

```

 ## How does it work?

 There are currently two blog posts that describe how to use `hamiltorch`:

 * For basic usage and an introduction please refer to my earlier post in 2019 ["hamiltorch: a PyTorch Python package for sampling"](https://adamcobb.github.io/journal/hamiltorch.html)

 * For a more recent summary and a focus on Bayesian neural networks, please see my post ["Scaling HMC to larger data sets"](https://adamcobb.github.io/journal/bnn.html)

 There are also notebook-style tutorials:

 * [Sampling from generic log probabilities](https://github.com/AdamCobb/hamiltorch/blob/master/notebooks/hamiltorch_log_prob_examples.ipynb)

 * [Sampling from `torch.nn.Module` (basic)](https://github.com/AdamCobb/hamiltorch/blob/master/notebooks/hamiltorch_Bayesian_NN_example.ipynb)

 * [Bayesian neural networks and split HMC](https://github.com/AdamCobb/hamiltorch/blob/master/notebooks/hamiltorch_split_HMC_BNN_example.ipynb)

 ## How to cite?

Please consider citing the following papers if you use `hamiltorch` in your research:

For symmetric splitting:

```

@article{cobb2020scaling,

  title={Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting},

  author={Cobb, Adam D and Jalaian, Brian},

  journal={Uncertainty in Artificial Intelligence},

  year={2021}

}

```

For RMHMC:

```

@article{cobb2019introducing,

  title={Introducing an Explicit Symplectic Integration Scheme for Riemannian Manifold Hamiltonian Monte Carlo},

  author={Cobb, Adam D and Baydin, At{\i}l{\i}m G{\"u}ne{\c{s}} and Markham, Andrew and Roberts, Stephen J},

  journal={arXiv preprint arXiv:1910.06243},

  year={2019}

}

```

## Star History

[![Star History Chart](https://api.star-history.com/svg?repos=AdamCobb/hamiltorch&type=Date)](https://star-history.com/#AdamCobb/hamiltorch&Date)

 ## Who developed hamiltorch?

 [Adam D Cobb](https://adamcobb.github.io)

 [Atılım Güneş Baydin](http://www.robots.ox.ac.uk/~gunes/)

 [Brian Jalaian](https://www.brianjalaian.com)