@article{Kishimoto_Bouneffouf_Marinescu_Ram_Rawat_Wistuba_Palmes_Botea_2022, title={Bandit Limited Discrepancy Search and Application to Machine Learning Pipeline Optimization}, volume={36}, url={https://ojs.aaai.org/index.php/AAAI/article/view/21263}, DOI={10.1609/aaai.v36i9.21263}, abstractNote={Optimizing a machine learning (ML) pipeline has been an important topic of AI and ML. Despite recent progress, pipeline optimization remains a challenging problem, due to potentially many combinations to consider as well as slow training and validation. We present the BLDS algorithm for optimized algorithm selection (ML operations) in a fixed ML pipeline structure. BLDS performs multi-fidelity optimization for selecting ML algorithms trained with smaller computational overhead, while controlling its pipeline search based on multi-armed bandit and limited discrepancy search. Our experiments on well-known classification benchmarks show that BLDS is superior to competing algorithms. We also combine BLDS with hyperparameter optimization, empirically showing the advantage of BLDS.}, number={9}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Kishimoto, Akihiro and Bouneffouf, Djallel and Marinescu, Radu and Ram, Parikshit and Rawat, Ambrish and Wistuba, Martin and Palmes, Paulito and Botea, Adi}, year={2022}, month={Jun.}, pages={10228-10237} }