{"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/inference-in-topic-models-sparsity-and-trade","title":"Inference in topic models: sparsity and trade-off","arxiv_id":"1512.03300","date":"2015-12-10","proceeding":null,"authors":["Khoat Than","Tu Bao Ho"],"abstract":"Topic models are popular for modeling discrete data (e.g., texts, images,\nvideos, links), and provide an efficient way to discover hidden\nstructures/semantics in massive data. One of the core problems in this field is\nthe posterior inference for individual data instances. This problem is\nparticularly important in streaming environments, but is often intractable. In\nthis paper, we investigate the use of the Frank-Wolfe algorithm (FW) for\nrecovering sparse solutions to posterior inference. From detailed elucidation\nof both theoretical and practical aspects, FW exhibits many interesting\nproperties which are beneficial to topic modeling. We then employ FW to design\nfast methods, including ML-FW, for learning latent Dirichlet allocation (LDA)\nat large scales. Extensive experiments show that to reach the same\npredictiveness level, ML-FW can perform tens to thousand times faster than\nexisting state-of-the-art methods for learning LDA from massive/streaming data.","url_abs":"http://arxiv.org/abs/1512.03300v1","url_pdf":"http://arxiv.org/pdf/1512.03300v1.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":"inference-in-topic-models-sparsity-and-trade","repo_url":"https://github.com/Khoat/OPE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"topic-models","task_name":"Topic Models"}],"methods":[{"method_slug":"lda","method_name":"LDA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}