Mining Robust Default Configurations for Resource-constrained AutoML
This addresses the need for efficient, resource-constrained AutoML by providing instant, robust configuration selection, which is incremental but offers practical gains.
The paper tackles the problem of automatically selecting high-performing model configurations for new tasks without online training, by mining a portfolio from diverse offline tasks. It demonstrates improvements over state-of-the-art methods across 62 datasets and outperforms hand-crafted defaults.
Automatic machine learning (AutoML) is a key enabler of the mass deployment of the next generation of machine learning systems. A key desideratum for future ML systems is the automatic selection of models and hyperparameters. We present a novel method of selecting performant configurations for a given task by performing offline autoML and mining over a diverse set of tasks. By mining the training tasks, we can select a compact portfolio of configurations that perform well over a wide variety of tasks, as well as learn a strategy to select portfolio configurations for yet-unseen tasks. The algorithm runs in a zero-shot manner, that is without training any models online except the chosen one. In a compute- or time-constrained setting, this virtually instant selection is highly performant. Further, we show that our approach is effective for warm-starting existing autoML platforms. In both settings, we demonstrate an improvement on the state-of-the-art by testing over 62 classification and regression datasets. We also demonstrate the utility of recommending data-dependent default configurations that outperform widely used hand-crafted defaults.