Because of its sample efficiency, Bayesian optimization (BO) has become a popular approach dealing with expensive black-box optimization problems, such as hyperparameter optimization (HPO). Recent empirical experiments showed that the loss landscapes of HPO problems tend to be more benign than previously assumed, i.e. in the best case uni-modal and convex, such that a BO framework could be more efficient if it can focus on those promising local regions. In this paper, we propose BOinG, a two-stage approach that is tailored toward mid-sized configuration spaces, as one encounters in many HPO problems. In the first stage, we build a scalable global surrogate model with a random forest to describe the overall landscape structure. Further, we choose a promising subregion via a bottom-up approach on the upper-level tree structure. In the second stage, a local model in this subregion is utilized to suggest the point to be evaluated next. Empirical experiments show that BOinG is able to exploit the structure of typical HPO problems and performs particularly well on mid-sized problems from synthetic functions and HPO.
翻译:由于抽样效率的提高,贝叶西亚优化(BO)已成为处理昂贵黑箱优化问题的流行方法,例如超光度优化(HPO),最近的实验实验表明,HPO问题的损失景观往往比先前假设的更为温和,即在最佳的单一模式和锥形情况下,如果BO框架能够侧重于有希望的地方区域,那么该框架的效率就会更高。在本文件中,我们提议BOinG,这是针对中等配置空间的两阶段方法,作为许多HPO问题的一次遭遇。在第一阶段,我们建立了一个可扩展的全球代孕模型,有随机森林来描述总体景观结构。此外,我们选择了一个有希望的次区域,在上层树结构上采用自下而上的办法,在第二阶段,利用这个次区域的当地模型来提出下一个评估点。Epirical实验表明,BOinG能够利用典型的HPO问题的结构,并特别很好地处理合成功能和HPO的中层问题。