Learning Feature-Parameter Mappings for Parameter Tuning via the Profile Expected Improvement
Jakob Bossek, Bernd Bischl, Tobias Wagner, Günter Rudolph · 2015
The majority of algorithms can be controlled or adjusted by parameters. Their values can substantially affect the algorithms' performance. Since the manual exploration of the parameter space is tedious -- even for few parameters -- several automatic procedures for parameter tuning have been proposed. Recent approaches also take into account some characteristic properties of the problem instances, frequently termed instance features.