{"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/estimation-from-indirect-supervision-with","title":"Estimation from Indirect Supervision with Linear Moments","arxiv_id":"1608.03100","date":"2016-08-10","proceeding":null,"authors":["Aditi Raghunathan","Roy Frostig","John Duchi","Percy Liang"],"abstract":"In structured prediction problems where we have indirect supervision of the\noutput, maximum marginal likelihood faces two computational obstacles:\nnon-convexity of the objective and intractability of even a single gradient\ncomputation. In this paper, we bypass both obstacles for a class of what we\ncall linear indirectly-supervised problems. Our approach is simple: we solve a\nlinear system to estimate sufficient statistics of the model, which we then use\nto estimate parameters via convex optimization. We analyze the statistical\nproperties of our approach and show empirically that it is effective in two\nsettings: learning with local privacy constraints and learning from low-cost\ncount-based annotations.","url_abs":"http://arxiv.org/abs/1608.03100v1","url_pdf":"http://arxiv.org/pdf/1608.03100v1.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":"estimation-from-indirect-supervision-with","repo_url":"https://worksheets.codalab.org/worksheets/0x6a264a96efea41158847eef9ec2f76bc","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"structured-prediction","task_name":"Structured Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.03100","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}