{"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/deep-amortized-inference-for-probabilistic","title":"Deep Amortized Inference for Probabilistic Programs","arxiv_id":"1610.05735","date":"2016-10-18","proceeding":null,"authors":["Daniel Ritchie","Paul Horsfall","Noah D. Goodman"],"abstract":"Probabilistic programming languages (PPLs) are a powerful modeling tool, able\nto represent any computable probability distribution. Unfortunately,\nprobabilistic program inference is often intractable, and existing PPLs mostly\nrely on expensive, approximate sampling-based methods. To alleviate this\nproblem, one could try to learn from past inferences, so that future inferences\nrun faster. This strategy is known as amortized inference; it has recently been\napplied to Bayesian networks and deep generative models. This paper proposes a\nsystem for amortized inference in PPLs. In our system, amortization comes in\nthe form of a parameterized guide program. Guide programs have similar\nstructure to the original program, but can have richer data flow, including\nneural network components. These networks can be optimized so that the guide\napproximately samples from the posterior distribution defined by the original\nprogram. We present a flexible interface for defining guide programs and a\nstochastic gradient-based scheme for optimizing guide parameters, as well as\nsome preliminary results on automatically deriving guide programs. We explore\nin detail the common machine learning pattern in which a 'local' model is\nspecified by 'global' random values and used to generate independent observed\ndata points; this gives rise to amortized local inference supporting global\nmodel learning.","url_abs":"http://arxiv.org/abs/1610.05735v1","url_pdf":"http://arxiv.org/pdf/1610.05735v1.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":"deep-amortized-inference-for-probabilistic","repo_url":"https://github.com/probmods/webppl-daipp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"probabilistic-programming","task_name":"Probabilistic Programming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1610.05735","atlas_url":"https://app.syntology.ai/?focus=1610.05735","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":"1610.05735"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1610.05735\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1610.05735"},"call":"get_concepts_for_paper(arxiv_id=\"1610.05735\")"}],"by_repo":[{"repo":"probmods/webppl-daipp","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"3ae2912104d1cb8961c896bbc8b924baf5af0c147461c9cbbb2ba8bb7fe98603","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}