Monte Carlo algorithms for optimal stopping and statistical learning

DOI10.1214/105051605000000043zbMATH Open1125.91050arXivmath/0408276OpenAlexW2038107520MaRDI QIDQ558680FDOQ558680

Daniel Egloff

Publication date: 13 July 2005

Published in: The Annals of Applied Probability (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/math/0408276

zbMATH Keywords

statistical learningempirical processesMonte Carlo methodsconcentration inequalitiesoptimal stoppingAmerican optionsuniform law of large numbersVapnik-Chervonenkis classes

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Monte Carlo methods (65C05) Derivative securities (option pricing, hedging, etc.) (91G20) Numerical methods (including Monte Carlo methods) (91G60) Stopping times; optimal stopping problems; gambling theory (60G40) Optimal stochastic control (93E20) Least squares and related methods for stochastic control systems (93E24)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Stochastic approximation methods for constrained and unconstrained systems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Optimum Character of the Sequential Probability Ratio Test
• Convergence of stochastic processes
• On methods of sieves and penalization
• Optimal global rates of convergence for nonparametric regression
• On the mathematical foundations of learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Risk bounds for model selection via penalization
• Sharper bounds for Gaussian and empirical processes
• A distribution-free theory of nonparametric regression
• About the constants in Talagrand's concentration inequalities for empirical processes.
• Local Rademacher complexities
• Uniform Central Limit Theorems
• Title not available (Why is that?)
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Variational inequalities and the pricing of American options
• On the theory of option pricing
• On the pricing of American options
• Title not available (Why is that?)
• Convergence rate of sieve estimates
• An analysis of a least squares regression method for American option pricing
• Title not available (Why is that?)
• Title not available (Why is that?)
• Option pricing: A simplified approach
• Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Title not available (Why is that?)
• Neural Network Learning
• PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$
• Monte Carlo valuation of American options
• Title not available (Why is that?)
• Efficient agnostic learning of neural networks with bounded fan-in
• Number of paths versus number of basis functions in American option pricing
• Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives
• On optimal stopping and free boundary problems
• Pricing American-style securities using simulation
• Inequalities for uniform deviations of averages from expectations with applications to nonparametric regression
• Learning and generalisation. With applications to neural networks.
• On Talagrand's deviation inequalities for product measures
• Title not available (Why is that?)
• Title not available (Why is that?)

Cited In (48)

• Algorithms for Optimal Control of Stochastic Switching Systems
• Discrete-type approximations for non-Markovian optimal stopping problems. II
• OPTIMAL MULTIPLE STOPPING AND VALUATION OF SWING OPTIONS
• When to stop learning? Bounding the stopping time in the PAC model
• Expected utility and catastrophic risk in a stochastic economy-climate model
• Nonexact oracle inequalities, \(r\)-learnability, and fast rates
• Rate of convergence of an empirical regression method for solving generalized backward stochastic differential equations
• A dynamic look-ahead Monte Carlo algorithm for pricing Bermudan options
• Mixing LSMC and PDE Methods to Price Bermudan Options
• AMERICAN OPTION PRICING WITH REGRESSION: CONVERGENCE ANALYSIS
• Monte-Carlo Valuation of American Options: Facts and New Algorithms to Improve Existing Methods
• Analysis of least squares regression estimates in case of additional errors in the variables
• Valuation of energy storage: an optimal switching approach
• A new learning algorithm for optimal stopping
• Pricing of American options in discrete time using least squares estimates with complexity penalties
• Regression methods in pricing American and Bermudan options using consumption processes
• Convergence of a Least‐Squares Monte Carlo Algorithm for Bounded Approximating Sets
• Bayesian Quickest Detection in Sensor Arrays
• Title not available (Why is that?)
• Sequential Design for Optimal Stopping Problems
• Unbiased optimal stopping via the MUSE
• Optimal Stopping of McKean--Vlasov Diffusions via Regression on Particle Systems
• A simulation-and-regression approach for stochastic dynamic programs with endogenous state variables
• Efficient algorithms of pathwise dynamic programming for decision optimization in mining operations
• On the rates of convergence of simulation-based optimization algorithms for optimal stopping problems
• On the convergence of the quasi-regression method: polynomial chaos and regularity
• ON THE CONSISTENCY OF REGRESSION‐BASED MONTE CARLO METHODS FOR PRICING BERMUDAN OPTIONS IN CASE OF ESTIMATED FINANCIAL MODELS
• Pricing Bermudan Options via Multilevel Approximation Methods
• Necessary and sufficient conditions for the pointwise convergence of nearest neighbor regression function estimates
• A regression-based smoothing spline Monte Carlo algorithm for pricing American options in discrete time
• Quantitative error estimates for a least-squares Monte Carlo algorithm for American option pricing
• Sensitivities for Bermudan options by regression methods
• A simulation approach to optimal stopping under partial information
• An efficient implementation of a least squares Monte Carlo method for valuing American-style options
• Pricing Asset Scheduling Flexibility using Optimal Switching
• General Error Estimates for the Longstaff–Schwartz Least-Squares Monte Carlo Algorithm
• Pricing high-dimensional Bermudan options using the stochastic grid method
• On data-based optimal stopping under stationarity and ergodicity
• Pricing Bermudan options by nonparametric regression: optimal rates of convergence for lower estimates
• Solving high-dimensional optimal stopping problems using deep learning
• An Introduction to Particle Methods with Financial Applications
• Sequential Design for Ranking Response Surfaces
• CONVERGENCE OF A LEAST‐SQUARES MONTE CARLO ALGORITHM FOR AMERICAN OPTION PRICING WITH DEPENDENT SAMPLE DATA
• The longstaff-Schwartz algorithm for Lévy models: results on fast and slow convergence
• MCMC design-based non-parametric regression for rare event. application to nested risk computations
• Pricing bounds and bang-bang analysis of the Polaris variable annuities
• JDOI variance reduction method and the pricing of American-style options
• Variance reduction for risk measures with importance sampling in nested simulation

   Recommendations

• Discrete-type approximations for non-Markovian optimal stopping problems. II 👍 👎
• A new learning algorithm for optimal stopping 👍 👎
• Deep optimal stopping 👍 👎
• Convergence of a Least‐Squares Monte Carlo Algorithm for Bounded Approximating Sets 👍 👎
• Optimal stopping via reinforced regression 👍 👎

This page was built for publication: Monte Carlo algorithms for optimal stopping and statistical learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q558680)