Publications Details

Publication Details

Auto folio: Algorithm configuration for algorithm selection

authored by
Marius Lindauer, Holger H. Hoos, Torsten Schaub, Frank Hutter

Algorithm selection (AS) techniques - which involve choosing from a set of algorithms the one expected to solve a given problem instance most efficiently - have substantially improved the state-of-the-art in solving many prominent AI problems, such as SAT, CSP, ASP, MAXSAT, and QBE Although several AS procedures have been introduced, not too surprisingly, none of them dominates all others across all AS scenarios. Furthermore, these procedures have parameters whose optimal values vary across AS scenarios. This holds specifically for the machine learning techniques that form the core of current AS procedures and for their hyperparameters. Therefore, to successfully apply AS to new problems, algorithms and benchmark sets, two questions need to be answered: (i) how to select an AS approach and (ii) how to set its parameters effectively. We address both of these problems simultaneously by using automated algorithm configuration. Specifically, we demonstrate that we can use algorithm configurators to automatically configure claspfolio 2, which implements a large variety of different AS approaches and their respective parameters in a single highly parameterized algorithm framework. We demonstrate that this approach, dubbed Auto Folio, can significantly improve the performance of claspfolio 2 on 11 out of the 12 scenarios from the Algorithm Selection Library and leads to new state-of-the-art algorithm selectors for 9 of these scenarios.

External Organisation(s)
University of Freiburg
University of British Columbia
University of Potsdam
Conference contribution
No. of pages
Publication date
Publication status
Peer reviewed
ASJC Scopus subject areas