{"type":"ScholarlyArticle","title":"Online Algorithm Selection","authors":[{"name":"Hans Degroote","slug":"hans-degroote","given":"Hans","family":"Degroote","affiliation":"KU Leuven , Department of Computer Science , Belgium; CODeS & imec-ITEC"}],"abstract":"Algorithm selection approaches have achieved impressive performance improvements in many areas of AI. Most of the literature considers the offline algorithm selection problem, where the initial selection model is never updated after training. However, new data from running algorithms on instances becomes available while an algorithm selection method is in use. In this extended abstract, the online algorithm selection problem is considered. In online algorithm selection, additional data can be processed, and the selection model can change over time. This abstract details the online algorithm setting, shows that it is a contextual multi-armed bandit, proposes a solution methodology, and empirically validates it.","doi":"10.24963/ijcai.2017/746","url":"https://ijcai.org/proceedings/2017/746","pdf":"https://ijcai.org/proceedings/2017/0746.pdf","markdown":"https://ijcai.org/proceedings/2017/746.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/746","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":746,"pages":{"first":5173,"last":5174},"keywords":["Artificial Intelligence: artificial intelligence","Artificial Intelligence: other","Artificial Intelligence: machine learning"],"videos":[],"references":[{"position":1,"raw":"[Bischl et al., 2016] Bernd Bischl, Pascal Kerschke, Lars Kotthoff, Marius Lindauer, Yuri Malitsky, Alexandre Fréchette, Holger Hoos, Frank Hutter, Kevin Leyton- Brown, Kevin Tierney, et al. Aslib: A benchmark library for algorithm selection. Artificial Intelligence, 237:41-58, 2016.","title":"Aslib: A benchmark library for algorithm selection","authors":"Bernd Bischl, Pascal Kerschke, Lars Kotthoff, Marius Lindauer, Yuri Malitsky, Alexandre Fréchette, Holger Hoos, Frank Hutter, Kevin Leyton-Brown, Kevin Tierney","year":"2016","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Malitsky, 2014] Yuri Malitsky. Evolving instance-specific algorithm configuration. In Instance-Specific Algorithm Configuration, pages 93-105. Springer, 2014.","title":"Evolving instance-specific algorithm configuration","authors":"Yuri Malitsky","year":"2014","venue":"Instance-Specific Algorithm Configuration","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}