Monte Carlo Algorithms for Optimal Stopping and Statistical Learning

Details Monte Carlo Algorithms for Optimal Stopping and Statistical Learning Monte Carlo Algorithms for Optimal Stopping and Statistical Learning

2004-08-20

arxiv.org/abs/math/0408276v1

Mathematics

Probability

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Monte Carlo Algorithms for Optimal Stopping and Statistical Learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Monte Carlo Algorithms for Optimal Stopping and Statistical Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Monte Carlo Algorithms for Optimal Stopping and Statistical Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-713703