Session Overview
In this talk, I will discuss the technical methods behind recent progress towards robust and efficient AutoML systems. After a brief recap of the early AutoML systems Auto-WEKA and Auto-sklearn, I will discuss the next generation, Auto-learn 2.0 and Auto-PyTorch. The talk will focus on the components that make these approaches far more efficient than Auto-sklearn 1.0, including practical considerations, multi-fidelity optimization, portfolio construction, and automated policy selection.
Overview
-
1
Evolution of Efficient and Robust AutoML Systems
-
Abstract & Bio
-
Evolution of Efficient and Robust AutoML Systems
-