DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Shin, Ha Yong | - |
dc.contributor.advisor | 신하용 | - |
dc.contributor.advisor | Park, Jin Kyoo | - |
dc.contributor.advisor | 박진규 | - |
dc.contributor.author | Jeong, Jihwan | - |
dc.date.accessioned | 2021-05-11T19:32:12Z | - |
dc.date.available | 2021-05-11T19:32:12Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=875270&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/282977 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 산업및시스템공학과, 2019.8,[iii, 25 p. :] | - |
dc.description.abstract | Bayesian optimization (BO) that employs the Gaussian process (GP) as a surrogate model has recently gained much attention. However, little research has been done to address the optimization of a multiple-component system where each component has a certain target value to meet. In this paper, our aim is to find the design parameter such that the response function is close to the target value for every component. To this end, the squared errors from the targets are aggregated to produce an objective function. Instead of modeling this objective using GP as in the standard BO formulation, we place the GP prior on the response function. As a result, the distribution over the objective function follows that of the weighted sum of non-central chi-squared random variables due to the inter-dependency between components. When components of the system are changed, the standard BO suffers inefficiency | - |
dc.description.abstract | however, our formulation enables us to retain a learned model, resulting in better efficiency. We compare the rates of convergence of different BO methods on two simulated test functions. The performance of our model is comparable to the standard BO when there is no change in the system, but the superiority of our method becomes clear when changes in the components occur. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Multiple-component system▼abayesian optimization▼asequential design of experiments▼ametamodeling▼agaussian processes | - |
dc.subject | 다중 컴포넌트 시스템▼a베이즈 최적화▼a순차적 실험 계획법▼a가우시안 프로세스▼a메타모델 기법 | - |
dc.title | Bayesian optimization for a multiple-component system with target values | - |
dc.title.alternative | 목푯값을 갖는 다중 성분 시스템의 베이즈 최적화 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :산업및시스템공학과, | - |
dc.contributor.alternativeauthor | 정지환 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.