Abdus Salam Khazi, Sebastian Pineda Arango, Josif Grabocka
TL;DR利用集成的神经网络元学习方法来优化超参数排序，取得了超参数优化方面的最新最优结果。
Abstract
Automatically optimizing the hyperparameters of machine learning algorithms is one of the primary open questions in AI. Existing work in hyperparameter optimization (HPO) trains surrogate models for approximating