{"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/conditionally-independent-multiresolution","title":"Conditionally Independent Multiresolution Gaussian Processes","arxiv_id":"1802.09086","date":"2018-02-25","proceeding":null,"authors":["Jalil Taghia","Thomas B. Schön"],"abstract":"The multiresolution Gaussian process (GP) has gained increasing attention as\na viable approach towards improving the quality of approximations in GPs that\nscale well to large-scale data. Most of the current constructions assume full\nindependence across resolutions. This assumption simplifies the inference, but\nit underestimates the uncertainties in transitioning from one resolution to\nanother. This in turn results in models which are prone to overfitting in the\nsense of excessive sensitivity to the chosen resolution, and predictions which\nare non-smooth at the boundaries. Our contribution is a new construction which\ninstead assumes conditional independence among GPs across resolutions. We show\nthat relaxing the full independence assumption enables robustness against\noverfitting, and that it delivers predictions that are smooth at the\nboundaries. Our new model is compared against current state of the art on 2\nsynthetic and 9 real-world datasets. In most cases, our new conditionally\nindependent construction performed favorably when compared against models based\non the full independence assumption. In particular, it exhibits little to no\nsigns of overfitting.","url_abs":"http://arxiv.org/abs/1802.09086v3","url_pdf":"http://arxiv.org/pdf/1802.09086v3.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":"conditionally-independent-multiresolution","repo_url":"https://github.com/jtaghia/ciMRGP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}