Unbiased optimal stopping via the MUSE

DOI10.1016/J.SPA.2022.12.007arXiv2106.02263OpenAlexW3169494828MaRDI QIDQ6184922FDOQ6184922

Authors: Zhengqing Zhou, Guanyang Wang, Jose Blanchet, Peter W. Glynn 

Publication date: 29 January 2024

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Abstract: We propose a new unbiased estimator for estimating the utility of the optimal stopping problem. The MUSE, short for Multilevel Unbiased Stopping Estimator, constructs the unbiased Multilevel Monte Carlo (MLMC) estimator at every stage of the optimal stopping problem in a backward recursive way. In contrast to traditional sequential methods, the MUSE can be implemented in parallel. We prove the MUSE has finite variance, finite computational complexity, and achieves $epsilon$-accuracy with $O(1/epsilo{n}^2)$ computational cost under mild conditions. We demonstrate MUSE empirically in an option pricing problem involving a high-dimensional input and the use of many parallel processors.

Full work available at URL: https://arxiv.org/abs/2106.02263

zbMATH Keywords

unbiased estimatoroptimal stoppingparallel computingmultilevel Monte Carlo

Mathematics Subject Classification ID

General considerations in statistical decision theory (62C05) Stopping times; optimal stopping problems; gambling theory (60G40) Optimal stopping in statistics (62L15)

Cites Work

• Bootstrap confidence intervals. With comments and a rejoinder by the authors
• Multilevel Monte Carlo Path Simulation
• Antithetic multilevel Monte Carlo estimation for multi-dimensional SDEs without Lévy area simulation
• Title not available (Why is that?)
• The Russian option: Reduced regret
• Policy iteration for american options: overview
• Monte Carlo algorithms for optimal stopping and statistical learning
• Number of paths versus number of basis functions in American option pricing
• Quantitative error estimates for a least-squares Monte Carlo algorithm for American option pricing
• Pricing American-style securities using simulation
• Multilevel dual approach for pricing American style derivatives
• Unbiased estimators and multilevel Monte Carlo
• Unbiased estimation with square root convergence for SDE models
• A general method for debiasing a Monte Carlo estimator
• Pricing high-dimensional Bermudan options using the stochastic grid method
• Decision-making under uncertainty: using MLMC for efficient estimation of EVPPI
• Unbiased Markov Chain Monte Carlo Methods with Couplings
• Exact estimation for Markov chain equilibrium expectations
• A secretary problem with two decision makers
• Title not available (Why is that?)
• Unbiased Markov chain Monte Carlo for intractable target distributions
• Unbiased Hamiltonian Monte Carlo with couplings
• Multilevel Monte Carlo estimation of the expected value of sample information
• Multilevel simulation based policy iteration for optimal stopping -- convergence and complexity
• MLMC for nested expectations

This page was built for publication: Unbiased optimal stopping via the MUSE

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6184922)