{"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/efficient-penalty-search-for-multiple","title":"Efficient penalty search for multiple changepoint problems","arxiv_id":"1412.3617","date":"2014-12-11","proceeding":null,"authors":["Kaylea Haynes","Idris A. Eckley","Paul Fearnhead"],"abstract":"In the multiple changepoint setting, various search methods have been\nproposed which involve optimising either a constrained or penalised cost\nfunction over possible numbers and locations of changepoints using dynamic\nprogramming. Such methods are typically computationally intensive. Recent work\nin the penalised optimisation setting has focussed on developing a\npruning-based approach which gives an improved computational cost that, under\ncertain conditions, is linear in the number of data points. Such an approach\nnaturally requires the specification of a penalty to avoid under/over-fitting.\nWork has been undertaken to identify the appropriate penalty choice for data\ngenerating processes with known distributional form, but in many applications\nthe model assumed for the data is not correct and these penalty choices are not\nalways appropriate. Consequently it is desirable to have an approach that\nenables us to compare segmentations for different choices of penalty. To this\nend we present a method to obtain optimal changepoint segmentations of data\nsequences for all penalty values across a continuous range. This permits an\nevaluation of the various segmentations to identify a suitably parsimonious\npenalty choice. The computational complexity of this approach can be linear in\nthe number of data points and linear in the difference between the number of\nchangepoints in the optimal segmentations for the smallest and largest penalty\nvalues. This can be orders of magnitude faster than alternative approaches that\nfind optimal segmentations for a range of the number of changepoints.","url_abs":"http://arxiv.org/abs/1412.3617v1","url_pdf":"http://arxiv.org/pdf/1412.3617v1.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":"efficient-penalty-search-for-multiple","repo_url":"https://github.com/hadley/15-student-papers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}