Population Based Training (PBT) is an efficient hyperparameter optimization algorithm. PBT is a single-objective algorithm, but many real-world hyperparameter optimization problems involve two or more conflicting objectives. In this work, we therefore introduce a multi-objective version of PBT, MO-PBT. Our experiments on diverse multi-objective hyperparameter optimization problems (Precision/Recall, Accuracy/Fairness, Accuracy/Adversarial Robustness) show that MO-PBT outperforms random search, single-objective PBT, and the state-of-the-art multi-objective hyperparameter optimization algorithm MO-ASHA.
@article{arxiv.2306.01436,
title = {Multi-Objective Population Based Training},
author = {Arkadiy Dushatskiy and Alexander Chebykin and Tanja Alderliesten and Peter A. N. Bosman},
journal= {arXiv preprint arXiv:2306.01436},
year = {2023}
}