TY  - CONF
T1  - Solver Tuning and Model Configuration
A1  - Barry, Michael
A1  - Abgottspon, Hubert
A1  - Schumann, René
ED  - Trollman, Frank
ED  - Turhan, Anni-Yasmin
TI  - Proceedings of the 41st German Conference on Artificial Intelligence (KI 2018)
T3  - Lecture Notes in Artificial Intelligence
Y1  - 2018
VL  - 1117
SP  - 141
EP  - 154
PB  - Springer, Cham
CY  - Berlin
SN  - 978-3-030-00110-0
UR  - https://link.springer.com/chapter/10.1007/978-3-030-00111-7_13
M2  - doi: https://doi.org/10.1007/978-3-030-00111-7_13
KW  - Evolutionary algorithm
KW  - machine learning
KW  - Mathematical solvers
KW  - Novelty search
KW  - Tuning mathematical solvers
N2  - This paper addresses the problem of tuning parameters of mathematical solvers to increase their performance. We investigate how solvers can be tuned for models that undergo two types of configuration: variable configuration and constraint configuration. For each type, we investigate search algorithms for data generation that emphasizes exploration or exploitation. We show the difficulties for solver tuning in constraint configuration and how data generation methods affects a training sets learning potential.
ER  -