搜索结果: 1-15 共查到“MCMC”相关记录60条 . 查询时间(0.093 秒)
中国科学院计算机网络信息中心专利：一种基于MCMC的并行分类方法
中国科学院计算机网络信息中心 专利 MCMC 并行分类
2023/8/24
本发明公开了一种基于MCMC的并行分类方法，包括：根据初始状态计算似然估计；根据似然估计计算出参数的后验概率；根据后验概率进行MCMC模拟运算，以当前状态为基础，产生新状态；根据新状态计算接受概率，并产生第一随机数，当第一随机数小于接受概率时，则下一时刻的状态为新状态，否则保持当前状态不变；产生同一列处理器中准备进行交换的马尔科夫链的标号；当处理器中的马尔科夫链参与了交换，则计算出交换概率，并产生...
基于贝叶斯MCMC方法的洪水频率分析及不确定性评估
洪水频率分析 GEV分布 MCMC 贝叶斯理论
2018/11/20
洪水设计值的计算和不确定性评估是水利工程规划和水资源管理的一个重要课题。以广义极值分布（GEV）作为洪水频率分布线型，通过基于Metropolis-Hastings抽样的贝叶斯马尔科夫链蒙特卡洛（MCMC）方法估计GEV分布参数和洪水设计值的后验概率分布，据此推求不同重现期条件下洪水设计值的点估计和区间估计。结果表明：贝叶斯MCMC方法的参数拟合效果与极大似然估计法相当，但由于其后验概率分布包含参...
Reversible MCMC on Markov equivalence classes of sparse directed acyclic graphs
Sparse graphical model Reversible Markov chain Markov equivalence class
2016/1/25
Graphical models are popular statistical tools which are used to represent dependent or causal complex systems. Statistically equivalent causal or directed graphical models are said to belong to a Mar...
Reversible MCMC on Markov equivalence classes of sparse directed acyclic graphs
Sparse graphical model Reversible Markov chain Markov equivalence class
2016/1/20
Graphical models are popular statistical tools which are used to represent dependent or causal complex systems. Statistically equivalent causal or directed graphical models are said to belong to a Mar...
针对马尔可夫链蒙特卡罗(MCMC)模型修正方法在待修正参数维数较高时不易收敛和计算效率低下的问题,建立了融合自适应算法和相关向量机的快速模型修正方法。基于广义无偏见先验分布,推导了待修正参数的后验分布;在标准MCMC方法的基础上,引入延缓拒绝算法以提高新样本接受概率;引入自适应算法以自主调整建议分布的带宽。通过相关向量机建立待修正参数与有限元模型理论计算值之间的回归模型,以提高模型修正的计算效率。...
Sometimes Average is Best:The Importance of Averaging for Prediction using MCMC Inference in Topic Modeling
Sometimes Average is Best Averaging for Prediction MCMC Inference Topic Modeling
2015/9/2
Markov chain Monte Carlo (MCMC) approximates the posterior distribution of latent variable models bygenerating many samples and averaging over them. In practice, however, itis often more convenient to...
MCMC LINKED WITH IMPLICIT SHAPE MODELS AND PLANE SWEEPING FOR 3D BUILDING FACADE INTERPRETATION IN IMAGE SEQUENCES
Markov Chain Monte Carlo Implicit Shape Models Plane Sweeping Facade Interpretation
2015/8/31
In this paper we propose to link Markov Chain Monte Carlo – MCMC in the spirit of (Dick, Torr, and Cipolla, 2004) with information from Implicit Shape Models – ISM (Leibe and Schiele, 2004) and with P...
MCMC LINKED WITH IMPLICIT SHAPE MODELS AND PLANE SWEEPING FOR 3D BUILDING FACADE INTERPRETATION IN IMAGE SEQUENCES
Markov Chain Monte Carlo Implicit Shape Models Plane Sweeping Facade Interpretation
2015/8/28
In this paper we propose to link Markov Chain Monte Carlo – MCMC in the spirit of (Dick, Torr, and Cipolla, 2004) with information from Implicit Shape Models – ISM (Leibe and Schiele, 2004) and with P...
纵横波联合叠前自适应MCMC反演方法
转换波 自适应马尔科夫链蒙特卡洛 非线性反演 精确Zoeppritz方程
2016/11/1
联合纵波（PP波）和转换波（PS波）地震资料进行AVO反演可降低解的非唯一性，提高反演的稳定性和AVO参数估算精度。文中提出了一种基于自适应马尔科夫链蒙特卡洛（MCMC）的纵横波叠前联合非线性反演方法，直接反演纵、横波速度及密度三个参数。该方法基于精确Zoeppritz方程，在贝叶斯框架下引入测井约束先验信息，在反演过程中使用自适应MCMC方法对贝叶斯后验概率密度进行抽样，并通过对收敛于后验概率密...
A New Proof of Convergence of MCMC via the Ergodic Theorem
Markov chain Monte Carlo Harris recurrence η-irreducibility
2015/7/6
A key result underlying the theory of MCMC is that any η-irreducible Markov chain having a transition density with respect to η and possessing a stationary distribution is automatically positive Harri...
Scaling MCMC Inference and Belief Propagation to Large, Dense Graphical Models
machine learning graphical models
2014/12/18
With the physical constraints of semiconductor-based electronics becoming increasingly limiting in the past decade, single-core CPUs have given way to multi-core and distributed computing platforms. A...
An application of MCMC simulation in mortality projection for populations with limited data
Bayesian MCMC modelling mortality projection WinBUGS
2014/11/26
Objective: IIn this paper, we investigate the use of Bayesian modeling and Markov chain Monte Carlo (MCMC) simulation, via the software WinBUGS, to project future mortality for populations with limite...
传统差分进化算法在优选水文模型参数时容易出现/早熟收敛0问题,基于马尔可夫链蒙特卡罗方法的差分进化算法)))DREAM算法,对嘉陵江流域降雨径流模型的参数优选问题进行了分析。结果发现,DREAM算法融合了自适应Metropolis方法的优点,能有效克服/早熟收敛0问题,适用于推求先验信息较少的复杂水文模型参数后验分布。
基于RJ-MCMC的DS-CDMA信号扩频码与信息序列盲估计
直扩码分多址 可逆跳跃 马尔科夫链蒙特卡罗 后验分布
2014/4/11
针对非合作低信噪比环境下的DS-CDMA信号参数估计问题，在分析信号模型的基础上，提出一种基于可逆跳跃的马尔科夫链蒙特卡罗(RJ-MCMC)扩频序列和信息序列联合估计算法。该算法通过建立信号参数和用户个数的联合后验分布模型，迭代抽样得到待估分布的样本，并有效地在不同维数的子空间中跳转，从而构造一条马尔科夫链，使其平稳分布为待估参数的后验分布。仿真结果表明，该算法在功率相同和不同的条件下均能适应较低...
MCMC methods for Gaussian process models using fast approximations for the likelihood
MCMC methods for Gaussian process models using fast approximations for the likelihood
2013/6/14
Gaussian Process (GP) models are a powerful and flexible tool for non-parametric regression and classification. Computation for GP models is intensive, since computing the posterior density, $\pi$, fo...