Adaptive importance sampling and control variates

Adaptive importance sampling and control variates
复制标题

自适应重要性采样和控制变量

DOI:
10.1016/j.jmaa.2019.123608
复制
发表时间:
2020
影响因子:
1.3
通讯作者:
Kawai Reiichiro
Kawai Reiichiro
中科院分区:
数学3区
文献类型:
--
作者:
Federico Barbacovi;Kohei Kikuta;福田一貴;Kawai Reiichiro

文献摘要

参考文献

被引文献

相似文献

我们构建并研究了一个自适应方差缩减框架,其中采用了重要性抽样和控制变量。这三条线(蒙特卡罗平均和两条方差减少参数搜索线)在单位超立方体上的均匀随机向量的公共序列上并行运行。鉴于这两种方差缩减技术通常以互补的方式有效,它们的组合应用有望扩大自适应方差缩减的适用性。当随机逼近以最优常数学习率运行时,我们推导出随着固定计算预算的增加,理论估计方差向其最小值的收敛速度。当计算预算无限时,我们推导出该算法在极限下通过学习率递减的随机逼近或样本平均逼近获得最小估计方差的充分条件。数值结果支持我们的理论研究结果,并说明所提出的框架的有效性。
We construct and investigate an adaptive variance reduction framework in which both importance sampling and control variates are employed. The three lines (Monte Carlo averaging and two variance reduction parameter search lines) run in parallel on a common sequence of uniform random vectors on the unit hypercube. Given that these two variance reduction techniques are effective often in a complementary way, their combined application is well expected to widen the applicability of adaptive variance reduction. We derive convergence rates of the theoretical estimator variance towards its minimum as a fixed computing budget increases, when stochastic approximation runs with optimal constant learning rates. We derive sufficient conditions for the proposed algorithm to attain the minimal estimator variance in the limit, by stochastic approximation with decreasing learning rates or by sample average approximation, when computing budget is unlimitedly available. Numerical results support our theoretical findings and illustrate the effectiveness of the proposed framework.
有限范围仿真的自适应控制变量
DOI: 10.1287/moor.1070.0251
发表时间: 2007
期刊: Math. Oper. Res.
影响因子: --
作者:
Sujin Kim;S. Henderson
通讯作者: S. Henderson
DOI: 10.1145/1734222.1734225
发表时间: 2010-04
期刊: ACM Trans. Model. Comput. Simul.
影响因子: --
作者:
Ray Kawai
通讯作者: Ray Kawai
使用样本平均逼近的自适应重要性采样加速
DOI: 10.1137/15m1047192
发表时间: 2017
期刊: SIAM J. Sci. Comput.
影响因子: --
作者:
Ray Kawai
通讯作者: Ray Kawai
具有两时间尺度随机逼近的 Levy 过程的自适应蒙特卡罗方差缩减
DOI: --
发表时间: 2008
期刊: Methodology and Computing in Applied Probability 10(2)
影响因子: --
作者:
Hiroshi Hirai;Hiroshi Hirai;Hiroshi Hirai;Hiroshi Hirai;平井広志;平井広志;Hiroshi Hirai;Hiroshi Hirai;Reiichiro Kawai;Reiichiro Kawai
通讯作者: Reiichiro Kawai
自适应蒙特卡罗方差缩减中的随机逼近
DOI: --
发表时间: 2021
期刊:
影响因子: --
作者:
Akira Morimoto;Ryuichi Ashino;Takeshi Mandai;Reiichiro Kawai
通讯作者: Reiichiro Kawai