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.

Cite

Text

Wu et al. "ChaCha for Online AutoML." International Conference on Machine Learning, 2021.

Markdown

[Wu et al. "ChaCha for Online AutoML." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/wu2021icml-chacha/)

BibTeX

@inproceedings{wu2021icml-chacha,
  title     = {{ChaCha for Online AutoML}},
  author    = {Wu, Qingyun and Wang, Chi and Langford, John and Mineiro, Paul and Rossi, Marco},
  booktitle = {International Conference on Machine Learning},
  year      = {2021},
  pages     = {11263-11273},
  volume    = {139},
  url       = {https://mlanthology.org/icml/2021/wu2021icml-chacha/}
}