搜索结果: 1-7 共查到“管理科学与工程 Monte Carlo”相关记录7条 . 查询时间(0.062 秒)
Efficient Monte Carlo Simulation of Security Prices
Efficient Monte Carlo Simulation Security Prices
2015/7/8
This paper provides an asymptotically efficient algorithm for the allocation of computing resources to the problem of Monte Carlo integration of continuous-time security prices. The tradeoff between i...
Importance Sampling for Monte Carlo Estimation of Quantiles
quantiles importance sampling large deviations.
2015/7/8
This paper is concerned with applying importance sampling as a variance reduction tool for computing extreme quantiles. A central limit theorem is derived for each of four proposed importance sampling...
Constrained Monte Carlo and the Method of Control Variates
Constrained Monte Carlo Method Control Variates
2015/7/8
A constrained Monte Carlo problem arises when one computes an expectation in the presence of a priori computable constraints on the expectations of quantities that are correlated with the estimand. Th...
Computing the Distribution Function of a Conditional Expectation via Monte Carlo: Discrete Conditioning Spaces
Probability algorithms distribution functions conditional expectation
2015/7/8
We examine different ways of numerically computing the distribution function of conditional expectations where the conditioning element takes values in a finite or countably infinite outcome space. Bo...
How to Deal with the Curse of Dimensionality of Likelihood Ratios in Monte Carlo Simulation
Cross-entropy Rare-event probability estimation Screening Simulation
2015/7/6
In this work we show how to resolve, at least partially, the curse of dimensionality of likelihood ratios (LRs) while using importance sampling (IS) to estimate the performance of high-dimensional Mon...
针对部分可观察马尔可夫决策过程(POMDPs) 的信念状态空间是一个双指数规模问题, 提出一种基于Monte
Carlo 粒子滤波的POMDPs 在线算法. 首先, 分别采用粒子滤波和粒子映射更新和扩展信念状态, 建立可达信念状态
与或树; 然后, 采用分支界限裁剪方法对信念状态与或树进行裁剪, 降低求解规模. 实验结果表明, 所提出算法具有较
低的误差率和较快的收敛性, 能够满足系统实时性...
基于单目视觉的机器人Monte Carlo自定位方法
移动机器人 SIFT 单目视觉 Monte Carlo定位
2014/9/15
针对单目视觉机器人的定位问题，提出了一种基于改进的尺度不变特征变换（SIFT）的Monte Carlo自定位方法。应用改进的SIFT方法提取特征，既能保证对图像光强变化、尺度缩放、三维视角和噪声具有不变性，又能减少SIFT算法产生的特征点及其抽取和匹配的时间。在机器人移动过程中，环境特征点的观测信息和里程计信息通过粒子滤波相融合，从而提高了机器人定位的速度和精度。实验结果验证了方法的有效性。