User menu

Accès à distance ? S'identifier sur le proxy UCLouvain

Mixed-effects modeling of optimisation algorithm performance

Primary tabs

Gagliolo, M. Legrand, Catherine [UCL] Birattari, M.

The learning curves of optimisation algorithms, plotting the evolution of the objective vs. runtime spent, can be viewed as a sample of longitudinal data. In this paper we describe mixed-effects modeling, a standard technique in longitudinal data analysis, and give an example of its application to algorithm performance modeling.

Document type Communication à un colloque (Conference Paper) – Présentation orale avec comité de sélection
Publication date 2009
Conference "Engineering Stochastic Local Search Algorithms. Designing, Implementing and Analyzing Effective Heuristics. Second International Workshop, SLS 2009", Brussels, Belgium (du 03/09/2008 au 04/09/2008)
Peer reviewed yes
Host document Stutzle, T.; Birattari, M.; Hoos, H.H.; ; "Engineering Stochastic Local Search Algorithms. Designing, Implementing and Analyzing Effective Heuristics. Second International Workshop, SLS 2009"- p. 150-154 (ISBN : 978-3-642-03750-4)
Collection Lecture Notes in Computer Science - 5752 (ISSN : 0302-9743)
Publisher Springer verlag
Publication status Publié
Affiliation UCL - EUEN/STAT - Institut de statistique
Links
Bibliographic reference Gagliolo, M. ; Legrand, Catherine ; Birattari, M.. Mixed-effects modeling of optimisation algorithm performance.Engineering Stochastic Local Search Algorithms. Designing, Implementing and Analyzing Effective Heuristics. Second International Workshop, SLS 2009 (Brussels, Belgium, du 03/09/2008 au 04/09/2008). In: Stutzle, T.; Birattari, M.; Hoos, H.H.;, Engineering Stochastic Local Search Algorithms. Designing, Implementing and Analyzing Effective Heuristics. Second International Workshop, SLS 2009, Springer verlag2009, p. 150-154
Permanent URL http://hdl.handle.net/2078.1/67480