{"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/sublinear-partition-estimation","title":"Sublinear Partition Estimation","arxiv_id":"1508.01596","date":"2015-08-07","proceeding":null,"authors":["Pushpendre Rastogi","Benjamin Van Durme"],"abstract":"The output scores of a neural network classifier are converted to\nprobabilities via normalizing over the scores of all competing categories.\nComputing this partition function, $Z$, is then linear in the number of\ncategories, which is problematic as real-world problem sets continue to grow in\ncategorical types, such as in visual object recognition or discriminative\nlanguage modeling. We propose three approaches for sublinear estimation of the\npartition function, based on approximate nearest neighbor search and kernel\nfeature maps and compare the performance of the proposed approaches\nempirically.","url_abs":"http://arxiv.org/abs/1508.01596v1","url_pdf":"http://arxiv.org/pdf/1508.01596v1.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":"sublinear-partition-estimation","repo_url":"https://github.com/SicongLiu/StreamingTopK","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"sublinear-partition-estimation","repo_url":"https://github.com/se4u/cylsh","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}