{"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/nested-mini-batch-k-means","title":"Nested Mini-Batch K-Means","arxiv_id":"1602.02934","date":"2016-02-09","proceeding":"NeurIPS 2016 12","authors":["James Newling","François Fleuret"],"abstract":"A new algorithm is proposed which accelerates the mini-batch k-means\nalgorithm of Sculley (2010) by using the distance bounding approach of Elkan\n(2003). We argue that, when incorporating distance bounds into a mini-batch\nalgorithm, already used data should preferentially be reused. To this end we\npropose using nested mini-batches, whereby data in a mini-batch at iteration t\nis automatically reused at iteration t+1.\n  Using nested mini-batches presents two difficulties. The first is that\nunbalanced use of data can bias estimates, which we resolve by ensuring that\neach data sample contributes exactly once to centroids. The second is in\nchoosing mini-batch sizes, which we address by balancing premature fine-tuning\nof centroids with redundancy induced slow-down. Experiments show that the\nresulting nmbatch algorithm is very effective, often arriving within 1% of the\nempirical minimum 100 times earlier than the standard mini-batch algorithm.","url_abs":"http://arxiv.org/abs/1602.02934v5","url_pdf":"http://arxiv.org/pdf/1602.02934v5.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":"nested-mini-batch-k-means","repo_url":"https://github.com/idiap/eakmeans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1602.02934","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}