The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training. Many methods for hyperparameter optimization (HPO) of iterative learners, including DNNs, attempt to solve this problem by querying and learning a response surface while searching for the optimum of that surface. However, many of these methods make myopic queries, do not consider prior knowledge about the response structure, and/or perform a biased cost-aware search, all of which exacerbate identifying the best-performing model when a total cost budget is specified. This paper proposes a novel approach referred to as {\bf B}udget-{\bf A}ware {\bf P}lanning for {\bf I}terative Learners (BAPI) to solve HPO problems under a constrained cost budget. BAPI is an efficient non-myopic Bayesian optimization solution that accounts for the budget and leverages the prior knowledge about the objective function and cost function to select better configurations and to take more informed decisions during the evaluation (training). Experiments on diverse HPO benchmarks for iterative learners show that BAPI performs better than state-of-the-art baselines in most cases.
翻译:深神经网络(DNN)和规模数据集的不断增长促使需要同时进行模型选择和培训的高效解决方案。许多迭代学习者(包括DNN)的超参数优化(HPO)方法(HPO)包括DNNS,试图通过查询和学习一个反应面来解决这个问题,同时寻找最佳表面的响应面。然而,许多这些方法都提出了近似问题,不考虑事先对反应结构的了解,和/或进行偏颇的成本认知搜索,所有这些都加剧了在列明总成本预算时确定最佳表现模式的必要性。本文建议采用新颖的方法,即对包括DNNNPs在内的迭代学习者的超参数优化(HPO)软件69f P}lanning(Bf P}laning),以便在有限的成本预算下解决HPO问题。BPI是一种高效的非微型海湾优化解决方案,它考虑到预算,并利用先前对目标功能和成本功能的了解来选择更好的配置,并在评估期间作出更知情的决定(培训)。对HPO的多数迭代生基准进行实验,显示比BPA案例的更好。</s>