Monte Carlo Algorithms for Optimal Stopping and Statistical Learning - Convergence Rates and Sample Complexity

21 Pages Posted: 15 Oct 2003

Abstract

In this article we extend the by now classical Longstaff-Schwartz algorithm for approximately solving high dimensional optimal stopping problems. We reformulate the problem of optimal stopping in discrete time as a generalized statistical learning problem. Within this setup we apply modern concentration inequalities for empirical means to study consistency criteria, convergence rates, and sample complexity estimates. Our results strengthen and extend earlier results obtained by Clement, Lamberton and Protter.

Keywords: Optimal stopping, American options, statistical learning, empirical processes, uniform law of large numbers, concentration inequalities, Vapnik-Chervonenkis classes, Monte Carlo methods.

JEL Classification: C6, C15, C61, C63, C65

Suggested Citation

Egloff, Daniel, Monte Carlo Algorithms for Optimal Stopping and Statistical Learning - Convergence Rates and Sample Complexity. Available at SSRN: https://ssrn.com/abstract=441720 or http://dx.doi.org/10.2139/ssrn.441720

Daniel Egloff (Contact Author)

QuantAlea GmbH ( email )

Wasserfuristrasse 42
Wiesendangen, 8542
Switzerland
+41 44 520 0117 (Phone)

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
393
Abstract Views
2,308
Rank
137,863
PlumX Metrics