20.500.12556/DiRROS-20434 Generalization ability of feature-based performance prediction models a statistical analysis across benchmarks Generalization ability of feature-based performance prediction models: a statistical analysis across benchmarks This study examines the generalization ability of algorithm performance prediction models across various bench-mark suites. Comparing the statistical similarity between the problem collections with the accuracy of performance prediction models that are based on exploratory landscape analysis features, we observe that there is a positive correlation between these two measures. Specifically, when the high-dimensional feature value distributions between training and testing suites lack statistical significance, the model tends to generalize well, in the sense that the testing errors are in the same range as the training errors. Two experiments validate these findings: one involving the standard benchmark suites, the BBOB and CEC collections, and another using five collections of affine combinations of BBOB problem instances. meta-learning single-objective optimization module importance metapodatki strojno učenje true false true IEEE ZDA Angleški jezik Slovenski jezik © 2024 IEEE Neznano 2024-09-16 12:42:04 2024-09-16 12:42:04 2024-09-17 04:02:08 0000-00-00 00:00:00 2024 0 0 Nasl. z nasl. zaslona; Opis vira z dne 10. 9. 2024; 8 str. 0000-00-00 PostprintKoncna Objavljeno NiDoloceno 0000-00-00 0000-00-00 2024-08-08 004.85 10.1109/CEC60901.2024.10611952 206945027 204216835 https://ieeexplore.ieee.org/document/10611952 1 8dc90050-7407-11ef-9d3a-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=28772 RAZ_Nikolikj_Ana_2024.pdf RAZ_Nikolikj_Ana_2024.pdf 1 CFAE608E802112036A4DFAC6B41B8FAB d1647fa89202a97593a4a6fc768f166d4f4ef64c009cf4b14307ea8d370a41b8 14df45d6-7409-11ef-9d3a-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=28775 Institut Jožef Stefan 0 0 0