{"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/compressed-nonnegative-matrix-factorization","title":"Compressed Nonnegative Matrix Factorization is Fast and Accurate","arxiv_id":"1505.04650","date":"2015-05-18","proceeding":null,"authors":["Mariano Tepper","Guillermo Sapiro"],"abstract":"Nonnegative matrix factorization (NMF) has an established reputation as a\nuseful data analysis technique in numerous applications. However, its usage in\npractical situations is undergoing challenges in recent years. The fundamental\nfactor to this is the increasingly growing size of the datasets available and\nneeded in the information sciences. To address this, in this work we propose to\nuse structured random compression, that is, random projections that exploit the\ndata structure, for two NMF variants: classical and separable. In separable NMF\n(SNMF) the left factors are a subset of the columns of the input matrix. We\npresent suitable formulations for each problem, dealing with different\nrepresentative algorithms within each one. We show that the resulting\ncompressed techniques are faster than their uncompressed variants, vastly\nreduce memory demands, and do not encompass any significant deterioration in\nperformance. The proposed structured random projections for SNMF allow to deal\nwith arbitrarily shaped large matrices, beyond the standard limit of\ntall-and-skinny matrices, granting access to very efficient computations in\nthis general setting. We accompany the algorithmic presentation with\ntheoretical foundations and numerous and diverse examples, showing the\nsuitability of the proposed approaches.","url_abs":"http://arxiv.org/abs/1505.04650v2","url_pdf":"http://arxiv.org/pdf/1505.04650v2.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":"compressed-nonnegative-matrix-factorization","repo_url":"https://github.com/prki/mastersthesis","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}