AINeutralarXiv – CS AI · 9h ago6/10
🧠
Conditional PED-ANOVA: Hyperparameter Importance in Hierarchical & Dynamic Search Spaces
Researchers propose conditional PED-ANOVA (condPED-ANOVA), a new framework for measuring hyperparameter importance in machine learning search spaces where parameters have conditional dependencies. The method addresses limitations of existing approaches by accurately handling cases where a hyperparameter's presence or domain depends on other hyperparameters, improving the reliability of AutoML systems.