{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/tensorflow-distributions","title":"TensorFlow Distributions","arxiv_id":"1711.10604","date":"2017-11-28","proceeding":null,"authors":["Joshua V. Dillon","Ian Langmore","Dustin Tran","Eugene Brevdo","Srinivas Vasudevan","Dave Moore","Brian Patton","Alex Alemi","Matt Hoffman","Rif A. Saurous"],"abstract":"The TensorFlow Distributions library implements a vision of probability\ntheory adapted to the modern deep-learning paradigm of end-to-end\ndifferentiable computation. Building on two basic abstractions, it offers\nflexible building blocks for probabilistic computation. Distributions provide\nfast, numerically stable methods for generating samples and computing\nstatistics, e.g., log density. Bijectors provide composable volume-tracking\ntransformations with automatic caching. Together these enable modular\nconstruction of high dimensional distributions and transformations not possible\nwith previous libraries (e.g., pixelCNNs, autoregressive flows, and reversible\nresidual networks). They are the workhorse behind deep probabilistic\nprogramming systems like Edward and empower fast black-box inference in\nprobabilistic models built on deep-network components. TensorFlow Distributions\nhas proven an important part of the TensorFlow toolkit within Google and in the\nbroader deep learning community.","url_abs":"http://arxiv.org/abs/1711.10604v1","url_pdf":"http://arxiv.org/pdf/1711.10604v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/acr42/Neural-Variational-Knowledge-Graphs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/hongseok-yang/probprog19","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/kampta/pytorch-distributions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/mukehvier/tensorflow-prob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/nicola-decao/s-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/nicola-decao/s-vae-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/tensorflow/probability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tensorflow-distributions","repo_url":"https://github.com/zhoudoao-bayes/tf-probability","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1711.10604","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}