2021
ICML
ICML 2021
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 βliveβ 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.
π
Interdisciplinary Bridge
β Artificial Intelligence and Machine Learning and Mathematics & Optimization
π§
Keyword Pioneer
β champion challenger
π
Cross-Pollinator
β Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio