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 β€˜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.

πŸŒ‰ Interdisciplinary Bridge β€” Artificial Intelligence and Machine Learning and Mathematics & Optimization
🧭 Keyword Pioneer β€” champion challenger
🐝 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