PSEO: Optimizing Post-Hoc Stacking Ensemble Through Hyperparameter Tuning
AAAI Conference on Artificial Intelligence (AAAI), 2026. Oral.
Overview
PSEO optimizes post-hoc stacking ensembles by selecting base models and tuning ensemble hyperparameters. It balances model diversity and predictive performance, then searches over multi-layer stacking strategies to adapt the ensemble to each task.