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，但其高昂的成本在现代DL场景中往往难以承受。因此，人工实验——依赖研究者直觉、领域知识和廉价初步探索——仍是优化超参数的主流方法。为解决HPO算法与DL研究者之间的这一脱节，我们提出PriorBand——一种专为DL设计的HPO算法，能够同时利用专家先验知识与廉价代理任务。实验表明，PriorBand在多个DL基准测试中均表现出高效性，并在信息性专家输入下展现性能提升，同时对低质量专家先验具有鲁棒性。