BriefGPT.xyz
Jun, 2023
PriorBand: 深度学习时代的实用超参数优化
PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning
HTML
PDF
Neeratyoy Mallik, Edward Bergman, Carl Hvarfner, Danny Stoll, Maciej Janowski...
TL;DR
为了缓解深度学习(HPO)算法与DL研究者之间的不一致，我们提出了一个专门针对DL的HPO算法PriorBand，将专家信念和便宜的代理任务结合起来，通过各种DL基准测试体现了PriorBand的效率和对专家知识的敏感性。
Abstract
Hyperparameters of
deep learning
(DL) pipelines are crucial for their downstream performance. While a large number of methods for
hyperparameter optimization
(HPO) have been developed, their incurred costs are of
→