Monte Carlo algorithms for optimal stopping and statistical learning
From MaRDI portal
Publication:558680
statistical learningempirical processesMonte Carlo methodsconcentration inequalitiesoptimal stoppingAmerican optionsuniform law of large numbersVapnik-Chervonenkis classes
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)
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.
Recommendations
Cites work
- scientific article; zbMATH DE number 3147888 (Why is no real title available?)
- scientific article; zbMATH DE number 3751685 (Why is no real title available?)
- scientific article; zbMATH DE number 44592 (Why is no real title available?)
- scientific article; zbMATH DE number 48727 (Why is no real title available?)
- scientific article; zbMATH DE number 51427 (Why is no real title available?)
- scientific article; zbMATH DE number 3607222 (Why is no real title available?)
- scientific article; zbMATH DE number 1222807 (Why is no real title available?)
- scientific article; zbMATH DE number 477682 (Why is no real title available?)
- scientific article; zbMATH DE number 1043533 (Why is no real title available?)
- scientific article; zbMATH DE number 1095739 (Why is no real title available?)
- scientific article; zbMATH DE number 1950575 (Why is no real title available?)
- scientific article; zbMATH DE number 1999206 (Why is no real title available?)
- scientific article; zbMATH DE number 2152981 (Why is no real title available?)
- scientific article; zbMATH DE number 1391397 (Why is no real title available?)
- scientific article; zbMATH DE number 3369559 (Why is no real title available?)
- A distribution-free theory of nonparametric regression
- About the constants in Talagrand's concentration inequalities for empirical processes.
- An analysis of a least squares regression method for American option pricing
- Convergence of stochastic processes
- Convergence rate of sieve estimates
- Efficient agnostic learning of neural networks with bounded fan-in
- Estimation of dependences based on empirical data. Transl. from the Russian by Samuel Kotz
- Inequalities for uniform deviations of averages from expectations with applications to nonparametric regression
- Learning and generalisation. With applications to neural networks.
- Local Rademacher complexities
- Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
- Monte Carlo valuation of American options
- Neural Network Learning
- Number of paths versus number of basis functions in American option pricing
- On Talagrand's deviation inequalities for product measures
- On methods of sieves and penalization
- On optimal stopping and free boundary problems
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- On the mathematical foundations of learning
- On the pricing of American options
- On the theory of option pricing
- Optimal global rates of convergence for nonparametric regression
- Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives
- Optimum Character of the Sequential Probability Ratio Test
- Option pricing: A simplified approach
- PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$
- Pricing American-style securities using simulation
- Risk bounds for model selection via penalization
- Sharper bounds for Gaussian and empirical processes
- Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
- Stochastic approximation methods for constrained and unconstrained systems
- Uniform Central Limit Theorems
- Variational inequalities and the pricing of American options
- Weak convergence and empirical processes. With applications to statistics
Cited in
(53)- Unbiased optimal stopping via the MUSE
- Efficient algorithms of pathwise dynamic programming for decision optimization in mining operations
- Rate of convergence of an empirical regression method for solving generalized backward stochastic differential equations
- Nonexact oracle inequalities, \(r\)-learnability, and fast rates
- Dynamic programming for optimal stopping via pseudo-regression
- On the rates of convergence of simulation-based optimization algorithms for optimal stopping problems
- OPTIMAL MULTIPLE STOPPING AND VALUATION OF SWING OPTIONS
- American option pricing with regression: convergence analysis
- Pricing of American options in discrete time using least squares estimates with complexity penalties
- On the convergence of the quasi-regression method: polynomial chaos and regularity
- A simulation approach to optimal stopping under partial information
- Regression methods in pricing American and Bermudan options using consumption processes
- Sequential design for optimal stopping problems
- Optimal stopping via reinforced regression
- Sequential design for ranking response surfaces
- Convergence of a least-squares Monte Carlo algorithm for American option pricing with dependent sample data
- Valuation of energy storage: an optimal switching approach
- Pricing Bermudan options by nonparametric regression: optimal rates of convergence for lower estimates
- On data-based optimal stopping under stationarity and ergodicity
- Pricing high-dimensional Bermudan options using the stochastic grid method
- Quantitative error estimates for a least-squares Monte Carlo algorithm for American option pricing
- JDOI variance reduction method and the pricing of American-style options
- A new learning algorithm for optimal stopping
- Variance reduction for risk measures with importance sampling in nested simulation
- Expected utility and catastrophic risk in a stochastic economy-climate model
- General error estimates for the Longstaff-Schwartz least-squares Monte Carlo algorithm
- Pricing Bermudan Options via Multilevel Approximation Methods
- Algorithms for optimal control of stochastic switching systems
- A dynamic look-ahead Monte Carlo algorithm for pricing Bermudan options
- Necessary and sufficient conditions for the pointwise convergence of nearest neighbor regression function estimates
- Sensitivities for Bermudan options by regression methods
- Analysis of least squares regression estimates in case of additional errors in the variables
- Semitractability of optimal stopping problems via a weighted stochastic mesh algorithm
- The longstaff-Schwartz algorithm for Lévy models: results on fast and slow convergence
- A regression-based smoothing spline Monte Carlo algorithm for pricing American options in discrete time
- Bayesian quickest detection in sensor arrays
- MCMC design-based non-parametric regression for rare event. application to nested risk computations
- Optimal stopping of McKean-Vlasov diffusions via regression on particle systems
- On the consistency of regression-based Monte Carlo methods for pricing Bermudan options in case of estimated financial models
- Mixing LSMC and PDE methods to price Bermudan options
- Convergence of a Least‐Squares Monte Carlo Algorithm for Bounded Approximating Sets
- An introduction to particle methods with financial applications
- When to stop learning? Bounding the stopping time in the PAC model
- A simulation-and-regression approach for stochastic dynamic programs with endogenous state variables
- Monte-Carlo valuation of American options: facts and new algorithms to improve existing methods
- Discrete-type approximations for non-Markovian optimal stopping problems. II
- An efficient implementation of a least squares Monte Carlo method for valuing American-style options
- Pricing bounds and bang-bang analysis of the Polaris variable annuities
- Solving high-dimensional optimal stopping problems using deep learning
- Stochastic mesh method for optimal stopping problems
- Solving optimal stopping problems under model uncertainty via empirical dual optimisation
- Pricing Asset Scheduling Flexibility using Optimal Switching
- scientific article; zbMATH DE number 5558051 (Why is no real title available?)
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)
