Code and Data Repository for A FAST Method for Nested Estimation
该软件展示了FAST方法的效果，该方法将嵌套估计的均方误差收敛速度从Γ^{-2/3}提升至Γ^{-4/5}，对运筹学和机器学习中的相关应用有价值。
The goal of this software is to demonstrate the effect of the jackkniFe-bAsed neSted simulaTion (FAST) method proposed in "A FAST Method for Nested Estimation" by Guo Liang, Jun Luo and Kun Zhang. Nested estimation involves estimating an expectation of a function of a conditional expectation, and has many important applications in operations research and machine learning. However, the mean squared error (MSE) of the standard nested simulation (SNS) is only of order Γ − 2 / 3 , where Γ is the total simulation budget. Our proposed FAST method improves the convergence speed to Γ − 4 / 5 . Each folder contains a README.md file for more specific information.