{"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/variational-dropout-via-empirical-bayes","title":"Variational Dropout via Empirical Bayes","arxiv_id":"1811.00596","date":"2018-11-01","proceeding":null,"authors":["Valery Kharitonov","Dmitry Molchanov","Dmitry Vetrov"],"abstract":"We study the Automatic Relevance Determination procedure applied to deep\nneural networks. We show that ARD applied to Bayesian DNNs with Gaussian\napproximate posterior distributions leads to a variational bound similar to\nthat of variational dropout, and in the case of a fixed dropout rate,\nobjectives are exactly the same. Experimental results show that the two\napproaches yield comparable results in practice even when the dropout rates are\ntrained. This leads to an alternative Bayesian interpretation of dropout and\nmitigates some of the theoretical issues that arise with the use of improper\npriors in the variational dropout model. Additionally, we explore the use of\nthe hierarchical priors in ARD and show that it helps achieve higher sparsity\nfor the same accuracy.","url_abs":"http://arxiv.org/abs/1811.00596v2","url_pdf":"http://arxiv.org/pdf/1811.00596v2.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":"variational-dropout-via-empirical-bayes","repo_url":"https://github.com/ivannz/cplxmodule","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"variational-dropout","method_name":"Variational Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}