{"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/unbiased-online-recurrent-optimization","title":"Unbiased Online Recurrent Optimization","arxiv_id":"1702.05043","date":"2017-02-16","proceeding":"ICLR 2018 1","authors":["Corentin Tallec","Yann Ollivier"],"abstract":"The novel Unbiased Online Recurrent Optimization (UORO) algorithm allows for\nonline learning of general recurrent computational graphs such as recurrent\nnetwork models. It works in a streaming fashion and avoids backtracking through\npast activations and inputs. UORO is computationally as costly as Truncated\nBackpropagation Through Time (truncated BPTT), a widespread algorithm for\nonline learning of recurrent networks. UORO is a modification of NoBackTrack\nthat bypasses the need for model sparsity and makes implementation easy in\ncurrent deep learning frameworks, even for complex models.\n  Like NoBackTrack, UORO provides unbiased gradient estimates; unbiasedness is\nthe core hypothesis in stochastic gradient descent theory, without which\nconvergence to a local optimum is not guaranteed. On the contrary, truncated\nBPTT does not provide this property, leading to possible divergence.\n  On synthetic tasks where truncated BPTT is shown to diverge, UORO converges.\nFor instance, when a parameter has a positive short-term but negative long-term\ninfluence, truncated BPTT diverges unless the truncation span is very\nsignificantly longer than the intrinsic temporal range of the interactions,\nwhile UORO performs well thanks to the unbiasedness of its gradients.","url_abs":"http://arxiv.org/abs/1702.05043v3","url_pdf":"http://arxiv.org/pdf/1702.05043v3.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":"unbiased-online-recurrent-optimization","repo_url":"https://github.com/ctallec/uoro","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"uoro","method_name":"UORO"}],"datasets_introduced":[],"methods_introduced":[{"slug":"uoro","name":"UORO","full_name":"Unbiased Online Recurrent Optimization"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.05043","atlas_url":"https://app.syntology.ai/?focus=1702.05043","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":"1702.05043"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1702.05043\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1702.05043"},"call":"get_concepts_for_paper(arxiv_id=\"1702.05043\")"}],"by_repo":[{"repo":"ctallec/uoro","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":"414bca7199c27d2b1ace155496e76fa6064adef3727160d630b22beb932283d5","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}