Title
Online Model Racing Based On Extreme Performance
Keywords
Algorithm portfolio; Extreme value theory; Online model selection; Racing algorithm
Abstract
Racing algorithms are often used for offline model selection, where models are compared in terms of their average performance over a collection of problems. In this paper, we present a new racing algorithm variant, Max-Race, which makes decisions based on the maximum performance of models. It is an online algorithm, whose goal is to optimally allocate computational resources in a portfolio of evolutionary algorithms, while solving a particular problem instance. It employs a hypothesis test based on extreme value theory in order to decide, which component algorithms to retire, while avoiding unnecessary computations. Experimental results confirm that Max-Race is able to identify the best individual with high precision and low computational overhead. When used as a scheme to select the best from a portfolio of algorithms, the results compare favorably to the ones of other popular algorithm portfolio approaches. © 2014 is held by the owner/author(s).
Publication Date
1-1-2014
Publication Title
GECCO 2014 - Proceedings of the 2014 Genetic and Evolutionary Computation Conference
Number of Pages
1351-1358
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/2576768.2598336
Copyright Status
Unknown
Socpus ID
84905683998 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84905683998
STARS Citation
Zhang, Tiantian; Georgiopoulos, Michael; and Anagnostopoulos, Georgios C., "Online Model Racing Based On Extreme Performance" (2014). Scopus Export 2010-2014. 9250.
https://stars.library.ucf.edu/scopus2010/9250