Aidong Zhao, Tianchen Gu, Zhaori Bi, Fan Yang, Changhao Yan, Xuan Zeng, Zixiao Lin, Wenchuang Hu, Dian Zhou
{"title":"D3PBO: Dynamic Domain Decomposition based Parallel Bayesian Optimization for Large-scale Analog Circuit Sizing","authors":"Aidong Zhao, Tianchen Gu, Zhaori Bi, Fan Yang, Changhao Yan, Xuan Zeng, Zixiao Lin, Wenchuang Hu, Dian Zhou","doi":"10.1145/3643811","DOIUrl":null,"url":null,"abstract":"<p>Bayesian optimization (BO) is an efficient global optimization method for expensive black-box functions. Whereas, the expansion for high-dimensional problems and large sample budgets still remains a severe challenge. In order to extend BO for large-scale analog circuit synthesis, a novel computationally efficient parallel BO method, D<sup>3</sup>PBO, is proposed for high-dimensional problems in this work. We introduce the dynamic domain decomposition method based on maximum variance between clusters. The search space is decomposed into subdomains progressively to limit the maximal number of observations in each domain. The promising domain is explored by multi-trust region based batch BO with the local Gaussian process (GP) model. As the domain decomposition progresses, the basin-shaped domain is identified using a GP-assisted quadratic regression method and exploited by the local search method BOBYQA to achieve faster convergence rate. The time complexity of D<sup>3</sup>PBO is constant for each iteration. Experiments demonstrate that D<sup>3</sup>PBO obtains better results with significant less runtime consumption compared to state-of-the-art methods. For the circuit optimization experiments, D<sup>3</sup>PBO achieves up to 10 × runtime speedup compared to TuRBO with better solutions.</p>","PeriodicalId":50944,"journal":{"name":"ACM Transactions on Design Automation of Electronic Systems","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACM Transactions on Design Automation of Electronic Systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1145/3643811","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0
Abstract
Bayesian optimization (BO) is an efficient global optimization method for expensive black-box functions. Whereas, the expansion for high-dimensional problems and large sample budgets still remains a severe challenge. In order to extend BO for large-scale analog circuit synthesis, a novel computationally efficient parallel BO method, D3PBO, is proposed for high-dimensional problems in this work. We introduce the dynamic domain decomposition method based on maximum variance between clusters. The search space is decomposed into subdomains progressively to limit the maximal number of observations in each domain. The promising domain is explored by multi-trust region based batch BO with the local Gaussian process (GP) model. As the domain decomposition progresses, the basin-shaped domain is identified using a GP-assisted quadratic regression method and exploited by the local search method BOBYQA to achieve faster convergence rate. The time complexity of D3PBO is constant for each iteration. Experiments demonstrate that D3PBO obtains better results with significant less runtime consumption compared to state-of-the-art methods. For the circuit optimization experiments, D3PBO achieves up to 10 × runtime speedup compared to TuRBO with better solutions.
贝叶斯优化(BO)是一种针对昂贵的黑盒函数的高效全局优化方法。然而,对高维问题和大样本预算的扩展仍然是一个严峻的挑战。为了将 BO 扩展到大规模模拟电路合成中,本研究针对高维问题提出了一种新型计算高效的并行 BO 方法 D3PBO。我们引入了基于簇间最大方差的动态域分解方法。搜索空间被逐步分解成子域,以限制每个域中观测值的最大数量。通过基于多信任区域的批量 BO 和本地高斯过程(GP)模型,探索有希望的域。随着域分解的进行,利用 GP 辅助二次回归方法识别出盆地状域,并通过局部搜索方法 BOBYQA 加以利用,以实现更快的收敛速度。D3PBO 的时间复杂度在每次迭代中都是恒定的。实验证明,与最先进的方法相比,D3PBO 能以更少的运行时间获得更好的结果。在电路优化实验中,与 TuRBO 相比,D3PBO 的运行速度提高了 10 倍,并获得了更好的解决方案。
期刊介绍:
TODAES is a premier ACM journal in design and automation of electronic systems. It publishes innovative work documenting significant research and development advances on the specification, design, analysis, simulation, testing, and evaluation of electronic systems, emphasizing a computer science/engineering orientation. Both theoretical analysis and practical solutions are welcome.