{"id":13477273,"url":"https://github.com/AdamCobb/hamiltorch","last_synced_at":"2025-03-27T04:33:06.543Z","repository":{"id":41375520,"uuid":"212798697","full_name":"AdamCobb/hamiltorch","owner":"AdamCobb","description":"PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks","archived":false,"fork":false,"pushed_at":"2024-08-28T16:34:36.000Z","size":3380,"stargazers_count":420,"open_issues_count":12,"forks_count":63,"subscribers_count":14,"default_branch":"master","last_synced_at":"2024-10-30T09:36:11.135Z","etag":null,"topics":["bnn","hmc","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AdamCobb.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-10-04T11:23:42.000Z","updated_at":"2024-10-28T18:38:55.000Z","dependencies_parsed_at":"2024-08-28T18:20:40.245Z","dependency_job_id":null,"html_url":"https://github.com/AdamCobb/hamiltorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamCobb%2Fhamiltorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamCobb%2Fhamiltorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamCobb%2Fhamiltorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AdamCobb%2Fhamiltorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AdamCobb","download_url":"https://codeload.github.com/AdamCobb/hamiltorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245785591,"owners_count":20671628,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["bnn","hmc","pytorch"],"created_at":"2024-07-31T16:01:40.479Z","updated_at":"2025-03-27T04:33:05.795Z","avatar_url":"https://github.com/AdamCobb.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook","\u003cspan id=\"head30\"\u003e3.4. Bayesian Inference\u003c/span\u003e"],"sub_categories":["\u003cspan id=\"head31\"\u003e3.4.1. MCMC\u003c/span\u003e"],"readme":"# hamiltorch\n\n\n PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks\n\n * Perform HMC in user-defined log probabilities and in PyTorch neural networks (objects inheriting from the `torch.nn.Module`).\n * Available sampling schemes:\n     * HMC\n     * No-U-Turn Sampler (currently adapts step-size only)\n     * Implicit RMHMC\n     * Explicit RMHMC\n     * Symmetric Split HMC\n\n ## How to install\n\n```\npip install git+https://github.com/AdamCobb/hamiltorch\n```\n\n ## How does it work?\n\n There are currently two blog posts that describe how to use `hamiltorch`:\n\n * 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)\n * 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)\n\n There are also notebook-style tutorials:\n\n * [Sampling from generic log probabilities](https://github.com/AdamCobb/hamiltorch/blob/master/notebooks/hamiltorch_log_prob_examples.ipynb)\n * [Sampling from `torch.nn.Module` (basic)](https://github.com/AdamCobb/hamiltorch/blob/master/notebooks/hamiltorch_Bayesian_NN_example.ipynb)\n * [Bayesian neural networks and split HMC](https://github.com/AdamCobb/hamiltorch/blob/master/notebooks/hamiltorch_split_HMC_BNN_example.ipynb)\n\n ## How to cite?\n\nPlease consider citing the following papers if you use `hamiltorch` in your research:\n\nFor symmetric splitting:\n```\n@article{cobb2020scaling,\n  title={Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting},\n  author={Cobb, Adam D and Jalaian, Brian},\n  journal={Uncertainty in Artificial Intelligence},\n  year={2021}\n}\n```\n\nFor RMHMC:\n```\n@article{cobb2019introducing,\n  title={Introducing an Explicit Symplectic Integration Scheme for Riemannian Manifold Hamiltonian Monte Carlo},\n  author={Cobb, Adam D and Baydin, At{\\i}l{\\i}m G{\\\"u}ne{\\c{s}} and Markham, Andrew and Roberts, Stephen J},\n  journal={arXiv preprint arXiv:1910.06243},\n  year={2019}\n}\n```\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=AdamCobb/hamiltorch\u0026type=Date)](https://star-history.com/#AdamCobb/hamiltorch\u0026Date)\n\n\n ## Who developed hamiltorch?\n\n [Adam D Cobb](https://adamcobb.github.io)\n\n [Atılım Güneş Baydin](http://www.robots.ox.ac.uk/~gunes/)\n\n [Brian Jalaian](https://www.brianjalaian.com)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAdamCobb%2Fhamiltorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAdamCobb%2Fhamiltorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAdamCobb%2Fhamiltorch/lists"}