Monte Carlo Algorithms for Optimal Stopping and Statistical Learning

2004/08/20 by Daniel Egloff, Egloff, Daniel · 2 citations
Mathematics · #60G40 #62G05 (Secondary) #91B28 #93E20 (Primary) 65C05 #93E24 #FOS: Mathematics #Probability (math.PR) #math.PR #msc:60G40 #msc:62G05 #msc:65C05 #msc:91B28 #msc:93E20 #msc:93E24

paper · pdf · doi:10.48550/arxiv.math/0408276

arxiv created 2004/08/20 · arxiv updated 2009/12/01

Abstract

We 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.

Cited by

• Deep Learning for the Multiple Optimal Stopping Problem
• CC-AOS: Cost- and Horizon-Conditioned Amortized Backward Induction for Finite-Horizon Optimal Stopping

Related

• Discrete-type approximations for non-Markovian optimal stopping problems: Part II
• Randomized optimal stopping algorithms and their convergence analysis
• Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods
• Optimal stopping under model uncertainty: randomized stopping times approach
• Optimal stopping of strong Markov processes