{"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/iterative-machine-teaching","title":"Iterative Machine Teaching","arxiv_id":"1705.10470","date":"2017-05-30","proceeding":"ICML 2017 8","authors":["Weiyang Liu","Bo Dai","Ahmad Humayun","Charlene Tay","Chen Yu","Linda B. Smith","James M. Rehg","Le Song"],"abstract":"In this paper, we consider the problem of machine teaching, the inverse\nproblem of machine learning. Different from traditional machine teaching which\nviews the learners as batch algorithms, we study a new paradigm where the\nlearner uses an iterative algorithm and a teacher can feed examples\nsequentially and intelligently based on the current performance of the learner.\nWe show that the teaching complexity in the iterative case is very different\nfrom that in the batch case. Instead of constructing a minimal training set for\nlearners, our iterative machine teaching focuses on achieving fast convergence\nin the learner model. Depending on the level of information the teacher has\nfrom the learner model, we design teaching algorithms which can provably reduce\nthe number of teaching examples and achieve faster convergence than learning\nwithout teachers. We also validate our theoretical findings with extensive\nexperiments on different data distribution and real image datasets.","url_abs":"http://arxiv.org/abs/1705.10470v3","url_pdf":"http://arxiv.org/pdf/1705.10470v3.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-machine-teaching","repo_url":"https://github.com/Ipsedo/IterativeMachineTeaching","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"iterative-machine-teaching","repo_url":"https://github.com/bariqi/Iterative-Mahine-Teaching-AML-Class","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10470","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}