B0979
Title: Adaptive-region sequential design with quantitative and qualitative factors in application to HPC configuration
Authors: Xinwei Deng - Virginia Tech (United States) [presenting]
Xia Cai - Hebei University of Science and Technology (China)
Devon Lin - Queen's University (Canada)
Yili Hong - Virginia Tech (United States)
Li Xu - Virginia Tech (United States)
Abstract: Motivated by the need to find optimal configurations in the high-performance computing (HPC) system, an adaptive-region sequential design (ARSD) is proposed for the optimization of computer experiments with qualitative and quantitative factors. Experiments with both qualitative and quantitative factors are also encountered in other applications. The proposed ARSD method considers a sequential design criterion under the additive Gaussian process to deal with both qualitative and quantitative factors. Moreover, the adaptiveness of the proposed sequential procedure allows the selection of the next design point from the adaptive design region, achieving a meaningful balance between exploitation and exploration for optimization. Theoretical justification of the adaptive design region is provided. The performance of the proposed method is evaluated by several numerical examples in simulations. The case study of HPC performance optimization further elaborates on the merits of the proposed method.
