{"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/on-the-good-reliability-of-an-interval-based","title":"On the good reliability of an interval-based metric to validate prediction uncertainty for machine learning regression tasks","arxiv_id":"2408.13089","date":"2024-08-23","proceeding":null,"authors":["Pascal Pernot"],"abstract":"This short study presents an opportunistic approach to a (more) reliable validation method for prediction uncertainty average calibration. Considering that variance-based calibration metrics (ZMS, NLL, RCE...) are quite sensitive to the presence of heavy tails in the uncertainty and error distributions, a shift is proposed to an interval-based metric, the Prediction Interval Coverage Probability (PICP). It is shown on a large ensemble of molecular properties datasets that (1) sets of z-scores are well represented by Student's-$t(\\nu)$ distributions, $\\nu$ being the number of degrees of freedom; (2) accurate estimation of 95 $\\%$ prediction intervals can be obtained by the simple $2\\sigma$ rule for $\\nu>3$; and (3) the resulting PICPs are more quickly and reliably tested than variance-based calibration metrics. Overall, this method enables to test 20 $\\%$ more datasets than ZMS testing. Conditional calibration is also assessed using the PICP approach.","url_abs":"https://arxiv.org/abs/2408.13089v2","url_pdf":"https://arxiv.org/pdf/2408.13089v2.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":"on-the-good-reliability-of-an-interval-based","repo_url":"https://github.com/ppernot/2024_picp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"prediction-intervals","task_name":"Prediction Intervals"}],"methods":[],"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}