{"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/unbounded-human-learning-optimal-scheduling","title":"Unbounded Human Learning: Optimal Scheduling for Spaced Repetition","arxiv_id":"1602.07032","date":"2016-02-23","proceeding":null,"authors":["Siddharth Reddy","Igor Labutov","Siddhartha Banerjee","Thorsten Joachims"],"abstract":"In the study of human learning, there is broad evidence that our ability to\nretain information improves with repeated exposure and decays with delay since\nlast exposure. This plays a crucial role in the design of educational software,\nleading to a trade-off between teaching new material and reviewing what has\nalready been taught. A common way to balance this trade-off is spaced\nrepetition, which uses periodic review of content to improve long-term\nretention. Though spaced repetition is widely used in practice, e.g., in\nelectronic flashcard software, there is little formal understanding of the\ndesign of these systems. Our paper addresses this gap in three ways. First, we\nmine log data from spaced repetition software to establish the functional\ndependence of retention on reinforcement and delay. Second, we use this memory\nmodel to develop a stochastic model for spaced repetition systems. We propose a\nqueueing network model of the Leitner system for reviewing flashcards, along\nwith a heuristic approximation that admits a tractable optimization problem for\nreview scheduling. Finally, we empirically evaluate our queueing model through\na Mechanical Turk experiment, verifying a key qualitative prediction of our\nmodel: the existence of a sharp phase transition in learning outcomes upon\nincreasing the rate of new item introductions.","url_abs":"http://arxiv.org/abs/1602.07032v2","url_pdf":"http://arxiv.org/pdf/1602.07032v2.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":"unbounded-human-learning-optimal-scheduling","repo_url":"https://github.com/rddy/leitnerq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"scheduling","task_name":"Scheduling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.07032","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}