{"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/iterative-amortized-inference","title":"Iterative Amortized Inference","arxiv_id":"1807.09356","date":"2018-07-24","proceeding":"ICML 2018 7","authors":["Joseph Marino","Yisong Yue","Stephan Mandt"],"abstract":"Inference models are a key component in scaling variational inference to deep\nlatent variable models, most notably as encoder networks in variational\nauto-encoders (VAEs). By replacing conventional optimization-based inference\nwith a learned model, inference is amortized over data examples and therefore\nmore computationally efficient. However, standard inference models are\nrestricted to direct mappings from data to approximate posterior estimates. The\nfailure of these models to reach fully optimized approximate posterior\nestimates results in an amortization gap. We aim toward closing this gap by\nproposing iterative inference models, which learn to perform inference\noptimization through repeatedly encoding gradients. Our approach generalizes\nstandard inference models in VAEs and provides insight into several empirical\nfindings, including top-down inference techniques. We demonstrate the inference\noptimization capabilities of iterative inference models and show that they\noutperform standard inference models on several benchmark data sets of images\nand text.","url_abs":"http://arxiv.org/abs/1807.09356v1","url_pdf":"http://arxiv.org/pdf/1807.09356v1.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":"iterative-amortized-inference","repo_url":"https://github.com/joelouismarino/iterative_inference","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"inference-optimization","task_name":"Inference Optimization"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.09356","atlas_url":"https://app.syntology.ai/?focus=1807.09356","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":"1807.09356"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1807.09356\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1807.09356"},"call":"get_concepts_for_paper(arxiv_id=\"1807.09356\")"}],"by_repo":[{"repo":"joelouismarino/iterative_inference","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":"59a35082aec31911430388772f1facd59421e794ef9f90ddd144141f336aafba","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}