“Hyper-parameter tuning in use is one of the crucial steps in the application of machine learning algorithms. In general, the tuning process is modeled as an optimization problem for which several methods have been proposed. For complex algorithms, the evaluation of a hyper-parameter configuration is expensive and their runtime is sped up through data sampling. In this paper, the effect of sample sizes to the results of hyper-parameter tuning process is investigated. Hyperparameters of Support Vector Machines are tuned on samples of different sizes generated from a dataset. Hausdorff distance is proposed for computing the differences between the results of hyper-parameter tuning on two samples of different size. 100 real-world datasets and two tuning methods (Random Search and Particle Swarm Optimization) are used in the experiments revealing some interesting relations between sample sizes and results of hyper-parameter tuning which open some promising directions for future investigation in this direction. Keywords: Sampling, Hyper-parameter tuning, Suport Vector Machines“
The proceedings can be accessed (here), the a manuscript can be downloaded here.
During the his visitation in Porto, Tomáš Horváth was invited talk at the Department of Informatics Engineering of the Faculty of Engineering of the University of Porto.
Telekom Innovation Laboratories
Data Analytics & Engineering | EU Labs Program
ELTE Budapest, Faculty of Informatics