Probabilistic Tools for Optimization of Classifiers on Large Data Sets

0523714 - ÚI 2021 IT eng A - Abstrakt
Kůrková, Věra - Sanguineti, M.
Probabilistic Tools for Optimization of Classifiers on Large Data Sets.
ODS 2019. Book of Abstracts. Genova: AIRO - Italian Operations Research Society, 2019. s. 75-75.
[ODS 2019: International Conference on Optimization and Decision Science /49./. 04.09.2019-07.09.2019, Genova]
Grant CEP: GA ČR(CZ) GA18-23827S
Institucionální podpora: RVO:67985807
Klíčová slova: Classification * Optimization of Computational Models * Concentration of Measures * Azuma-Hoeffding Inequality

The number of classification tasks on a finite domain (representing a set of vectors of features, measurements, or observations) grows exponentially with its size. However, for a given application area relevance of many such tasks might be very low or negligible. A probabilistic framework is introduced, modeling prior knowledge about probabilities that a presence of some features implies a property described by one of the classes. Impact of increasing sizes of domains on correlations between input-output mappings of computational models and randomly-chosen classifiers is analyzed. It is proven that for large domains the correlations are sharply concentrated around their mean values. Probabilistic bounds are derived via implications of the Azuma-Hoeffding Inequality, holding also without the ”naive Bayes assumption”. It is shown that the performance of random classifiers is almost deterministic, in the sense that either a given class of computational models can approximate well almost all tasks or none of them. Consequences for the choice of optimal computational models are derived
Trvalý link: http://hdl.handle.net/11104/0308024