@inproceedings{262fc85bb35d47d2b22e298049d3b993,
title = "ChaCha for Online AutoML",
abstract = "We propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings. ChaCha handles the process of determining a champion and scheduling a set of 'live' challengers over time based on sample complexity bounds. It is guaranteed to have sublinear regret after the optimal configuration is added into consideration by an application-dependent oracle based on the champions. Empirically, we show that ChaCha provides good performance across a wide array of datasets when optimizing over featurization and hyperparameter decisions.",
author = "Qingyun Wu and Chi Wang and John Langford and Paul Mineiro and Marco Rossi",
note = "Funding Information: The authors would like to thank Akshay Krishnamurthy for the discussions about this work and the anonymous reviewers for their revision suggestions. Publisher Copyright: Copyright {\textcopyright} 2021 by the author(s); 38th International Conference on Machine Learning, ICML 2021 ; Conference date: 18-07-2021 Through 24-07-2021",
year = "2021",
language = "English (US)",
series = "Proceedings of Machine Learning Research",
publisher = "ML Research Press",
pages = "11263--11273",
booktitle = "Proceedings of the 38th International Conference on Machine Learning, ICML 2021",
}