서브메뉴
검색
Analyzing Sampling in Stochastic Optimization: Importance Sampling and Statistical Inference
Analyzing Sampling in Stochastic Optimization: Importance Sampling and Statistical Inference
상세정보
- 자료유형
- 학위논문
- Control Number
- 0015492143
- International Standard Book Number
- 9781088306994
- Dewey Decimal Classification Number
- 512
- Main Entry-Personal Name
- Yu, Yang.
- Publication, Distribution, etc. (Imprint
- [Sl] : The University of North Carolina at Chapel Hill, 2019
- Publication, Distribution, etc. (Imprint
- Ann Arbor : ProQuest Dissertations & Theses, 2019
- Physical Description
- 113 p
- General Note
- Source: Dissertations Abstracts International, Volume: 81-04, Section: B.
- General Note
- Advisor: Lu, Shu
- Dissertation Note
- Thesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2019.
- Restrictions on Access Note
- This item must not be sold to any third party vendors.
- Restrictions on Access Note
- This item must not be added to any third party search indexes.
- Summary, Etc.
- 요약The objective function of a stochastic optimization problem usually involves an expectation of random variables which cannot be calculated directly. When this is the case, a common approach is to replace the expectation with a sample average approximation. However, sometimes there are difficulties in using such a sample average approximation to achieve certain goals. This dissertation studies two specific problems. In the first problem, we aim to solve a minimization problem whose objective function is the probability of an undesired rare event. To accurately estimate this rare event probability by Monte Carlo simulation, an extremely large sample is required, which is expensive to implement. An importance sampling scheme based on the theory of large deviations is developed to efficiently reduce the sample size and thus reduce the computational cost. The convergence of a sequence of approximation problems is also studied, through which a good initial point to the minimization problem can be found. We also study the buffered probability of exceedance as an alternative risk measure instead of the ordinary probability. Under conditions, the analogous minimization problem can be formulated into a convex problem.In the second problem, we focus on a two-stage stochastic linear programming problem, where the objective function has to be approximated by a sample average function with a random sample of the corresponding random variables. However, such a sample average function is not smooth enough to estimate the Hessian of the objective function which is needed to calculate the confidence intervals for the true solution. To overcome this difficulty, the sample average function is smoothed by its convolution with a kernel function. Methods to compute confidence intervals for the true solution are then developed based on inference methods for stochastic variational inequalities.
- Subject Added Entry-Topical Term
- Operations research
- Subject Added Entry-Topical Term
- Monte Carlo simulation
- Subject Added Entry-Topical Term
- Linear programming
- Subject Added Entry-Topical Term
- Statistical inference
- Subject Added Entry-Topical Term
- Stochastic models
- Subject Added Entry-Topical Term
- Optimization
- Added Entry-Corporate Name
- The University of North Carolina at Chapel Hill Statistics and Operations Research
- Host Item Entry
- Dissertations Abstracts International. 81-04B.
- Host Item Entry
- Dissertation Abstract International
- Electronic Location and Access
- 로그인을 한후 보실 수 있는 자료입니다.
- Control Number
- joongbu:565608
MARC
008200131s2019 c eng d■001000015492143
■00520200217181546
■020 ▼a9781088306994
■035 ▼a(MiAaPQ)AAI13900068
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a512
■1001 ▼aYu, Yang.
■24510▼aAnalyzing Sampling in Stochastic Optimization: Importance Sampling and Statistical Inference
■260 ▼a[Sl]▼bThe University of North Carolina at Chapel Hill▼c2019
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2019
■300 ▼a113 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 81-04, Section: B.
■500 ▼aAdvisor: Lu, Shu
■5021 ▼aThesis (Ph.D.)--The University of North Carolina at Chapel Hill, 2019.
■506 ▼aThis item must not be sold to any third party vendors.
■506 ▼aThis item must not be added to any third party search indexes.
■520 ▼aThe objective function of a stochastic optimization problem usually involves an expectation of random variables which cannot be calculated directly. When this is the case, a common approach is to replace the expectation with a sample average approximation. However, sometimes there are difficulties in using such a sample average approximation to achieve certain goals. This dissertation studies two specific problems. In the first problem, we aim to solve a minimization problem whose objective function is the probability of an undesired rare event. To accurately estimate this rare event probability by Monte Carlo simulation, an extremely large sample is required, which is expensive to implement. An importance sampling scheme based on the theory of large deviations is developed to efficiently reduce the sample size and thus reduce the computational cost. The convergence of a sequence of approximation problems is also studied, through which a good initial point to the minimization problem can be found. We also study the buffered probability of exceedance as an alternative risk measure instead of the ordinary probability. Under conditions, the analogous minimization problem can be formulated into a convex problem.In the second problem, we focus on a two-stage stochastic linear programming problem, where the objective function has to be approximated by a sample average function with a random sample of the corresponding random variables. However, such a sample average function is not smooth enough to estimate the Hessian of the objective function which is needed to calculate the confidence intervals for the true solution. To overcome this difficulty, the sample average function is smoothed by its convolution with a kernel function. Methods to compute confidence intervals for the true solution are then developed based on inference methods for stochastic variational inequalities.
■590 ▼aSchool code: 0153.
■650 4▼aOperations research
■650 4▼aMonte Carlo simulation
■650 4▼aLinear programming
■650 4▼aStatistical inference
■650 4▼aStochastic models
■650 4▼aOptimization
■690 ▼a0796
■71020▼aThe University of North Carolina at Chapel Hill▼bStatistics and Operations Research.
■7730 ▼tDissertations Abstracts International▼g81-04B.
■773 ▼tDissertation Abstract International
■790 ▼a0153
■791 ▼aPh.D.
■792 ▼a2019
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T15492143▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
■980 ▼a202002▼f2020