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 often untenable for modern DL. Consequently, manual experimentation is still the most prevalent approach to optimize hyperparameters, relying on the researcher's intuition, domain knowledge, and cheap preliminary explorations. To resolve this misalignment between HPO algorithms and DL researchers, we propose PriorBand, an HPO algorithm tailored to DL, able to utilize both expert beliefs and cheap proxy tasks. Empirically, we demonstrate PriorBand's efficiency across a range of DL benchmarks and show its gains under informative expert input and robustness against poor expert beliefs

翻译：深度学习（DL）流程的超参数对其下游性能至关重要。尽管已有大量超参数优化（HPO）方法被开发出来，但其产生的成本对于现代深度学习而言往往难以承受。因此，手动实验仍然是最常用的超参数优化方法，依赖于研究者的直觉、领域知识以及廉价的初步探索。为解决HPO算法与深度学习研究者之间的这种不匹配问题，我们提出了PriorBand——一种专为深度学习定制的HPO算法，能够同时利用专家先验知识和廉价代理任务。通过实验，我们证明了PriorBand在多种深度学习基准测试中的效率，并展示了其在专家信息输入有效时的性能提升，以及在专家先验不佳时的鲁棒性。