标题： FastBO：具有自适应保真度识别的快速HPO和NAS 显示英文标题

标题： FastBO: Fast HPO and NAS with Adaptive Fidelity Identification

摘要： 超参数优化（HPO）和神经网络架构搜索（NAS）在获得最先进的机器学习模型方面具有强大的能力，其中贝叶斯优化（BO）是一种主流方法。将BO扩展到多保真设置已成为一个新兴的研究课题，但面临的一个挑战是如何为每个超参数配置确定适当的保真度以拟合代理模型。为了解决这一挑战，我们提出了一种名为FastBO的多保真BO方法，该方法自适应地为每个配置决定保真度，并高效地提供强大的性能。这些优势基于每个配置的新颖概念：高效点和饱和点。我们还表明，我们的自适应保真度识别策略提供了一种将任何单保真度方法扩展到多保真度设置的方法，突显了其通用性和适用性。 显示英文摘要

摘要： Hyperparameter optimization (HPO) and neural architecture search (NAS) are powerful in attaining state-of-the-art machine learning models, with Bayesian optimization (BO) standing out as a mainstream method. Extending BO into the multi-fidelity setting has been an emerging research topic, but faces the challenge of determining an appropriate fidelity for each hyperparameter configuration to fit the surrogate model. To tackle the challenge, we propose a multi-fidelity BO method named FastBO, which adaptively decides the fidelity for each configuration and efficiently offers strong performance. The advantages are achieved based on the novel concepts of efficient point and saturation point for each configuration.We also show that our adaptive fidelity identification strategy provides a way to extend any single-fidelity method to the multi-fidelity setting, highlighting its generality and applicability.