{"id":21892972,"url":"https://github.com/chunyuanli/psgld","last_synced_at":"2025-03-22T03:40:24.210Z","repository":{"id":92718273,"uuid":"52742539","full_name":"ChunyuanLI/pSGLD","owner":"ChunyuanLI","description":"AAAI \u0026 CVPR 2016: Preconditioned Stochastic Gradient Langevin Dynamics (pSGLD)","archived":false,"fork":false,"pushed_at":"2018-09-16T02:02:58.000Z","size":28709,"stargazers_count":35,"open_issues_count":2,"forks_count":12,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-03T00:54:34.335Z","etag":null,"topics":["mcmc","preconditioner","sampling-methods","stochastic-gradient-descent"],"latest_commit_sha":null,"homepage":"","language":"Matlab","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ChunyuanLI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2016-02-28T20:34:31.000Z","updated_at":"2023-07-25T14:00:34.000Z","dependencies_parsed_at":null,"dependency_job_id":"e7ab8876-3fc8-4195-ad8e-b696e83242c8","html_url":"https://github.com/ChunyuanLI/pSGLD","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/ChunyuanLI%2FpSGLD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChunyuanLI%2FpSGLD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChunyuanLI%2FpSGLD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChunyuanLI%2FpSGLD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChunyuanLI","download_url":"https://codeload.github.com/ChunyuanLI/pSGLD/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244902929,"owners_count":20529114,"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":["mcmc","preconditioner","sampling-methods","stochastic-gradient-descent"],"created_at":"2024-11-28T13:00:11.722Z","updated_at":"2025-03-22T03:40:24.192Z","avatar_url":"https://github.com/ChunyuanLI.png","language":"Matlab","funding_links":[],"categories":[],"sub_categories":[],"readme":"# pSGLD\nPreconditioned Stochastic Gradient Langevin Dynamics (pSGLD)\n\nLinks:\n[Implementation on TensorFlow Website](https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/StochasticGradientLangevinDynamics)\n\n## Simulation (2D Gaussian Example in Figure 1 of the paper)\n- Simulation 1 provides _Average Absolute Error of Sample Covariance_ vs _AutoCorrelation Time (ACT)_\n- Simulation 2 provides first 600 samples from SGLD and pSGLD\n\n\u003cimg src=\"/simulation/2D/figure/pSGLD.png\" data-canonical-src=\"/simulation/2D/figure/pSGLD.png\" width=\"460\" height=\"250\" /\u003e\n\n## Experiments on Deep Neural Networks (Keep updating)\n- Start to run 'test_FNN_mnist.m' to test a 2-layer FNN with 400 hidden units each . \n- You may also modify line 'linSizes  = [400 400 data.outSize]' to other configurations. \n\n\n## Citation\nPlease cite our AAAI paper if it helps your research:\n\n\t@inproceedings{pSGLD_AAAI2016,\n\t  title={Preconditioned stochastic gradient Langevin dynamics for deep neural networks},\n\t  author={Li, Chunyuan and Chen, Changyou and Carlson, David and Carin, Lawrence},\n\t  booktitle={AAAI},\n\t  Year  = {2016}\n\t}\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchunyuanli%2Fpsgld","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchunyuanli%2Fpsgld","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchunyuanli%2Fpsgld/lists"}