{"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/yes-but-did-it-work-evaluating-variational","title":"Yes, but Did It Work?: Evaluating Variational Inference","arxiv_id":"1802.02538","date":"2018-02-07","proceeding":"ICML 2018 7","authors":["Yuling Yao","Aki Vehtari","Daniel Simpson","Andrew Gelman"],"abstract":"While it's always possible to compute a variational approximation to a\nposterior distribution, it can be difficult to discover problems with this\napproximation. We propose two diagnostic algorithms to alleviate this problem.\nThe Pareto-smoothed importance sampling (PSIS) diagnostic gives a goodness of\nfit measurement for joint distributions, while simultaneously improving the\nerror in the estimate. The variational simulation-based calibration (VSBC)\nassesses the average performance of point estimates.","url_abs":"http://arxiv.org/abs/1802.02538v2","url_pdf":"http://arxiv.org/pdf/1802.02538v2.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":"yes-but-did-it-work-evaluating-variational","repo_url":"https://github.com/yao-yl/Evaluating-Variational-Inference","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1802.02538","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}