{"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/high-quality-prediction-intervals-for-deep","title":"High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach","arxiv_id":"1802.07167","date":"2018-02-20","proceeding":"ICML 2018 7","authors":["Tim Pearce","Mohamed Zaki","Alexandra Brintrup","Andy Neely"],"abstract":"This paper considers the generation of prediction intervals (PIs) by neural\nnetworks for quantifying uncertainty in regression tasks. It is axiomatic that\nhigh-quality PIs should be as narrow as possible, whilst capturing a specified\nportion of data. We derive a loss function directly from this axiom that\nrequires no distributional assumption. We show how its form derives from a\nlikelihood principle, that it can be used with gradient descent, and that model\nuncertainty is accounted for in ensembled form. Benchmark experiments show the\nmethod outperforms current state-of-the-art uncertainty quantification methods,\nreducing average PI width by over 10%.","url_abs":"http://arxiv.org/abs/1802.07167v3","url_pdf":"http://arxiv.org/pdf/1802.07167v3.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":"high-quality-prediction-intervals-for-deep","repo_url":"https://github.com/TeaPearce/Deep_Learning_Prediction_Intervals","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"form","task_name":"Form"},{"task_slug":"prediction-intervals","task_name":"Prediction Intervals"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1802.07167","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}