{"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/online-learning-for-distribution-free","title":"Online Learning for Distribution-Free Prediction","arxiv_id":"1703.05060","date":"2017-03-15","proceeding":null,"authors":["Dave Zachariah","Petre Stoica","Thomas B. Schön"],"abstract":"We develop an online learning method for prediction, which is important in\nproblems with large and/or streaming data sets. We formulate the learning\napproach using a covariance-fitting methodology, and show that the resulting\npredictor has desirable computational and distribution-free properties: It is\nimplemented online with a runtime that scales linearly in the number of\nsamples; has a constant memory requirement; avoids local minima problems; and\nprunes away redundant feature dimensions without relying on restrictive\nassumptions on the data distribution. In conjunction with the split conformal\napproach, it also produces distribution-free prediction confidence intervals in\na computationally efficient manner. The method is demonstrated on both real and\nsynthetic datasets.","url_abs":"http://arxiv.org/abs/1703.05060v1","url_pdf":"http://arxiv.org/pdf/1703.05060v1.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":"online-learning-for-distribution-free","repo_url":"https://github.com/dzachariah/online-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}