{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/inference-compilation-and-universal","title":"Inference Compilation and Universal Probabilistic Programming","arxiv_id":"1610.09900","date":"2016-10-31","proceeding":null,"authors":["Tuan Anh Le","Atilim Gunes Baydin","Frank Wood"],"abstract":"We introduce a method for using deep neural networks to amortize the cost of\ninference in models from the family induced by universal probabilistic\nprogramming languages, establishing a framework that combines the strengths of\nprobabilistic programming and deep learning methods. We call what we do\n\"compilation of inference\" because our method transforms a denotational\nspecification of an inference problem in the form of a probabilistic program\nwritten in a universal programming language into a trained neural network\ndenoted in a neural network specification language. When at test time this\nneural network is fed observational data and executed, it performs approximate\ninference in the original model specified by the probabilistic program. Our\ntraining objective and learning procedure are designed to allow the trained\nneural network to be used as a proposal distribution in a sequential importance\nsampling inference engine. We illustrate our method on mixture models and\nCaptcha solving and show significant speedups in the efficiency of inference.","url_abs":"http://arxiv.org/abs/1610.09900v2","url_pdf":"http://arxiv.org/pdf/1610.09900v2.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":"inference-compilation-and-universal","repo_url":"https://github.com/plai-group/pyprob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"inference-compilation-and-universal","repo_url":"https://github.com/probprog/pyprob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"inference-compilation-and-universal","repo_url":"https://github.com/pyprob/pyprob","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"inference-compilation-and-universal","repo_url":"https://github.com/wsgharvey/pyro-infcomp-examples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1610.09900","atlas_url":"https://app.syntology.ai/?focus=1610.09900","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1610.09900"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1610.09900\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1610.09900"},"call":"get_concepts_for_paper(arxiv_id=\"1610.09900\")"}],"by_repo":[{"repo":"plai-group/pyprob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"probprog/pyprob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1907.03382"],"harvested_for_calls":[{"arxiv_id":"1907.03382","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1907.03382"},"call":"get_harvested_code_for_paper(arxiv_id=\"1907.03382\")"}]},{"repo":"pyprob/pyprob","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1907.03382"],"harvested_for_calls":[{"arxiv_id":"1907.03382","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1907.03382"},"call":"get_harvested_code_for_paper(arxiv_id=\"1907.03382\")"}]},{"repo":"wsgharvey/pyro-infcomp-examples","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3b9f6c1b513b49cb5aab7dd2ccafe54146affa6997eacc9243c90234c965f804","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}