{"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/model-selection-in-bayesian-neural-networks","title":"Model Selection in Bayesian Neural Networks via Horseshoe Priors","arxiv_id":"1705.10388","date":"2017-05-29","proceeding":null,"authors":["Soumya Ghosh","Finale Doshi-Velez"],"abstract":"Bayesian Neural Networks (BNNs) have recently received increasing attention\nfor their ability to provide well-calibrated posterior uncertainties. However,\nmodel selection---even choosing the number of nodes---remains an open question.\nIn this work, we apply a horseshoe prior over node pre-activations of a\nBayesian neural network, which effectively turns off nodes that do not help\nexplain the data. We demonstrate that our prior prevents the BNN from\nunder-fitting even when the number of nodes required is grossly over-estimated.\nMoreover, this model selection over the number of nodes doesn't come at the\nexpense of predictive or computational performance; in fact, we learn smaller\nnetworks with comparable predictive performance to current approaches.","url_abs":"http://arxiv.org/abs/1705.10388v1","url_pdf":"http://arxiv.org/pdf/1705.10388v1.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":"model-selection-in-bayesian-neural-networks","repo_url":"https://github.com/SoumyaTGhosh/hs-bnn-public","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.10388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}