Monte Carlo Algorithms for Optimal Stopping and Statistical Learning

Simple item page
dc.creatorEgloff, Daniel
dc.date2004-08-20
dc.date.accessioned2026-07-07T05:11:25Z
dc.date.available2026-07-07T05:11:25Z
dc.descriptionWe extend the Longstaff-Schwartz algorithm for approximately solving optimal stopping problems on high-dimensional state spaces. We reformulate the optimal stopping problem for Markov processes in discrete time as a generalized statistical learning problem. Within this setup we apply deviation inequalities for suprema of empirical processes to derive consistency criteria, and to estimate the convergence rate and sample complexity. Our results strengthen and extend earlier results.
dc.identifierhttps://arxiv.org/abs/math/0408276
dc.identifierhttp://arxiv.org/abs/math/0408276
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/72237
dc.subjectProbability
dc.subject91B28, 60G40, 93E20 (Primary) 65C05, 93E24, 62G05 (Secondary)
dc.titleMonte Carlo Algorithms for Optimal Stopping and Statistical Learning
dc.typetext

Files

Collections

arXiv