{"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/stability-selection-for-component-wise","title":"Stability selection for component-wise gradient boosting in multiple dimensions","arxiv_id":"1611.10171","date":"2016-11-30","proceeding":null,"authors":["Janek Thomas","Andreas Mayr","Bernd Bischl","Matthias Schmid","Adam Smith","Benjamin Hofner"],"abstract":"We present a new algorithm for boosting generalized additive models for\nlocation, scale and shape (GAMLSS) that allows to incorporate stability\nselection, an increasingly popular way to obtain stable sets of covariates\nwhile controlling the per-family error rate (PFER). The model is fitted\nrepeatedly to subsampled data and variables with high selection frequencies are\nextracted. To apply stability selection to boosted GAMLSS, we develop a new\n\"noncyclical\" fitting algorithm that incorporates an additional selection step\nof the best-fitting distribution parameter in each iteration. This new\nalgorithms has the additional advantage that optimizing the tuning parameters\nof boosting is reduced from a multi-dimensional to a one-dimensional problem\nwith vastly decreased complexity. The performance of the novel algorithm is\nevaluated in an extensive simulation study. We apply this new algorithm to a\nstudy to estimate abundance of common eider in Massachusetts, USA, featuring\nexcess zeros, overdispersion, non-linearity and spatio-temporal structures.\nEider abundance is estimated via boosted GAMLSS, allowing both mean and\noverdispersion to be regressed on covariates. Stability selection is used to\nobtain a sparse set of stable predictors.","url_abs":"http://arxiv.org/abs/1611.10171v1","url_pdf":"http://arxiv.org/pdf/1611.10171v1.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":"stability-selection-for-component-wise","repo_url":"https://github.com/boost-R/gamboostLSS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"additive-models","task_name":"Additive models"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.10171","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}