Variance reduction for discretised diffusions via regression
arXiv:1510.03141 · doi:10.1016/j.jmaa.2017.09.002
Abstract
In this paper we present a novel approach towards variance reduction for discretised diffusion processes. The proposed approach involves specially constructed control variates and allows for a significant reduction in the variance for the terminal functionals. In this way the complexity order of the standard Monte Carlo algorithm ( in the case of a first order scheme and in the case of a second order scheme) can be reduced down to for any with being the precision to be achieved. These theoretical results are illustrated by several numerical examples.
References in corpus (4)
- Weak approximation of stochastic differential equations and application to derivative pricing
- A new weak approximation scheme of stochastic differential equations and the Runge-Kutta method
- An operator approach for Markov chain weak approximations with an application to infinite activity Lévy driven SDEs
- A Discrete-Time Clark-Ocone Formula and its Application to an Error Analysis
Cited by in corpus (5)
- Unbiased deep solvers for linear parametric PDEs
- Neural variance reduction for stochastic differential equations
- Regression-based variance reduction approach for strong approximation schemes
- Stratified regression-based variance reduction approach for weak approximation schemes
- Truncated control variates for weak approximation schemes