Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/15998
Full metadata record
???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
---|---|---|
dc.contributor.advisor | 張淑惠 | |
dc.contributor.author | Kuei-Ling Huang | en |
dc.contributor.author | 黃貴鈴 | zh_TW |
dc.date.accessioned | 2021-06-07T17:57:36Z | - |
dc.date.copyright | 2012-09-17 | |
dc.date.issued | 2012 | |
dc.date.submitted | 2012-08-13 | |
dc.identifier.citation | [1]Liang, F., Liu,C., Carrol, R.J. (2010) “Advanced Markov Chain Monte Carlo Method :Learning from Past Samples” John Wiley and Sons Ltd
[2] Carlo, M. (2004).” Markov Chain Monte Carlo and Gibbs Sampling.” Notes, (April). [3] Liang, F., Liu,C., Carrol, R.J. (2007) “Stochastic Approximation in Monte Carlo Computation” Journal of the American Statistical Association 102,305-320 [4] Earlab, D.J. Deema, M. W. (2005) “ Parallel Tempering: Theory, applications, and new perspectives ”Phys.Chem.7, 3910-3916 [5] Goswami, G., Liu, J.S. (2007) “On Learning strategies for evolutionary Monte Carlo ” Stat Comput 17,23-38 [6]Yu, K.(2011) “Efficient p-value evaluation for resampling-based test ”Biostatistics,12, 3, 582-593 [7]Li, Y.,Mascagni, M.,Gorin, A.(2009)”A decentralized parallel implementation for parallel tempering algorithm ”Parallel Computing, 35, 269-283 [8] Dobson, A. J., Barnett, A. G (2008) “An Introduction to Generalized Linear Models” Chapman & Hall/CRC [9] Woodard, D.B., Schmidler, S.C., Huber,M. (2009)“Conditions for Rapid Mixing of Parallel and Simulated Tempering on Multimodal Distributions” The Annals of Applied Probability ,19,617-640 [10]Chib, S., Edward, G.(1995)”Understanding the Metropolis-Hastings Algorithm” The American Statistican ,49,327-335 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/15998 | - |
dc.description.abstract | Metropolis-Hastings演算法是基於建構馬可夫鏈自多變量分布產生一序列隨機樣本的方法,當分布為崎嶇不平或是多峰分布的維度很高時,Metropolis-Hastings演算法很容易會陷在某個區域性的單峰分布,在文獻中,有數種改善Metropolis-Hasting演算法的演算法被提出。舉例來說,平行調整演算法是利用輔助變數改善Metropolis-Hastings演算法的模擬方法;而動態漸近蒙地卡羅演算法利用過去樣本資訊改造Metropolis-Hastings演算法。在此研究中,藉由結合此兩種方法,同時利用輔助變數與過去樣本資訊提出新的演算法。模擬研究為比較新的演算法與上述兩種演算法的表現。模擬的結果顯示動態漸近蒙地卡羅演算法在多峰分布的峰有覆蓋時表現不佳,多峰分布的峰無覆蓋時其表現佳;平行調整演算法在多峰分布的峰有無覆蓋皆表現佳,而結合兩種方法的表現依賴交換發生率及候選函數。 | zh_TW |
dc.description.abstract | Metropolis-Hastings algorithm is established based on a Markov chain method to generate a series of random samples from multivariate distributions. When the distributions are rugged or the number of dimensions in multimodal distributions is high, Metropolis-Hastings algorithm is likely to be trapped locally by a certain unimodal distributions. There are several algorithms proposed to improve Metropolis-Hastings algorithm in literature. For example, parallel tempering is a simulation method which uses auxiliary variables to modify Metropolis-Hastings algorithm. Alternatively, the stochastic approximation Monte Carlo algorithm exploits the past sample information to adapt Metropolis-Hastings algorithm. In this study, a new algorithm is proposed by combing these two methods for using both information from auxiliary variables and past samples. A simulation study is conducted to investigate and compare the performance of the new algorithm and the abovementioned algorithms. The simulation results show that the performance of stochastic approximation Monte Carlo algorithm for the multimodal distribution modes coverage is poor but its performance is better for modes without covering. Parallel tempering performs well for both situations, while performance of the combined method is dependent on the exchange of incidence and proposal function. | en |
dc.description.provenance | Made available in DSpace on 2021-06-07T17:57:36Z (GMT). No. of bitstreams: 1 ntu-101-R99849013-1.pdf: 1996811 bytes, checksum: 563a09c55a4911c33d4992cc8b707a14 (MD5) Previous issue date: 2012 | en |
dc.description.tableofcontents | 第一章 緒論 1
第一節 研究背景 1 第二節 研究目的 3 第二章 文獻回顧 4 第一節 Metropolis-Hastings 演算法 4 第二節 動態漸近蒙地卡羅演算法 9 第三節 平行調整演算法 13 第三章 研究方法 17 第一節 結合SAMC與平行調整演算法在多峰分布下的分布模擬 …………………………………………………………..17 第四章 模擬研究 21 第一節 模擬步驟與設定 21 第二節 模擬結果 37 第五章 結果與討論 65 參考文獻 67 | |
dc.language.iso | zh-TW | |
dc.title | 探討結合動態漸近蒙地卡羅演算法與平行調整演算法在多峰分布抽樣的表現 | zh_TW |
dc.title | Combining stochastic approximation monte carlo and parallel tempering algorithms in sampling multimodal distributions | en |
dc.type | Thesis | |
dc.date.schoolyear | 100-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 戴政,鄭明燕,陳秀熙 | |
dc.subject.keyword | Metropolis-Hastings演算法,平行調整演算法,動態漸近蒙地卡羅演算法,多峰分布, | zh_TW |
dc.subject.keyword | Metropolis-Hastings algorithms,parallel tempering,stochastic approximation Monte Carlo algorithm,multimodal distribution, | en |
dc.relation.page | 67 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2012-08-13 | |
dc.contributor.author-college | 公共衛生學院 | zh_TW |
dc.contributor.author-dept | 流行病學與預防醫學研究所 | zh_TW |
Appears in Collections: | 流行病學與預防醫學研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-101-1.pdf Restricted Access | 1.95 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.