Regression Methods for Stochastic Control Problems and Their Convergence Analysis

In this paper we develop several regression algorithms for solving general stochastic optimal control problems via Monte Carlo. This type of algorithm is particularly useful for problems with a high-dimensional state space and complex dependence structure of the underlying Markov process with respect to some control. The main idea behind the algorithms is to simulate a set of trajectories under some reference measure and to use the Bellman principle combined with fast methods for approximating conditional expectations and functional optimization. Theoretical properties of the presented algorithms are investigated, and the convergence to the optimal solution is proved under some assumptions. Finally, the presented methods are applied in a numerical example of a high-dimensional controlled Bermudan basket option in a financial market with a large investor.

[1]  Simon Lysbjerg Hansen,et al.  A Malliavin-based Monte-Carlo Approach for Numerical Solution of Stochastic Control Problems: Experiences from Merton's Problem , 2005 .

[2]  D. Belomestny,et al.  TRUE UPPER BOUNDS FOR BERMUDAN PRODUCTS VIA NON‐NESTED MONTE CARLO , 2009 .

[3]  Daniel Egloff.  Monte Carlo algorithms for optimal stopping and statistical learning , 2004, math/0408276.

[4]  R. Carmona,et al.  OPTIMAL MULTIPLE STOPPING AND VALUATION OF SWING OPTIONS , 2008 .

[5]  Philip Protter,et al.  An analysis of a least squares regression method for American option pricing , 2002, Finance Stochastics.

[6]  Michael Monoyios.  Option pricing with transaction costs using a Markov chain approximation , 2004 .

[7]  N. Touzi,et al.  Kernel estimation of Greek weights by parameter randomization , 2007, 0710.4392.

[8]  M. Kohler,et al.  A dynamic look-ahead Monte Carlo algorithm for pricing Bermudan options , 2007, 0710.3640.

[9]  John N. Tsitsiklis,et al.  Regression methods for pricing complex American-style options , 2001, IEEE Trans. Neural Networks.

[10]  V. Spokoiny,et al.  Regression methods in pricing American and Bermudan options using consumption processes , 2009 .

[11]  A. W. van der Vaart,et al.  Uniform Central Limit Theorems , 2001 .

[12]  P. Glasserman,et al.  A Sotchastic Mesh Method for Pricing High-Dimensional American Options , 2004 .

[13]  Martin B. Haugh,et al.  Pricing American Options: A Duality Approach , 2001, Oper. Res..

[14]  P. Glasserman,et al.  Pricing American-style securities using simulation , 1997 .

[15]  Paul Glasserman,et al.  Monte Carlo Methods in Financial Engineering , 2003 .

[16]  J. Carriére.  Valuation of the early-exercise price for options using simulations and nonparametric regression , 1996 .

[17]  Francis A. Longstaff,et al.  Valuing American Options by Simulation: A Simple Least-Squares Approach , 2001 .

[18]  Bruno Bouchard,et al.  On the Malliavin approach to Monte Carlo approximation of conditional expectations , 2004, Finance Stochastics.

[19]  Bruno Bouchard,et al.  Maturity randomization for stochastic control problems , 2005 .

[20]  Christian Bender,et al.  An iterative algorithm for multiple stopping: Convergence and stability , 2004 .

[21]  John Schoenmakers,et al.  Iterative construction of the optimal Bermudan stopping time , 2006, Finance Stochastics.

[22]  N. Meinshausen,et al.  MONTE CARLO METHODS FOR THE VALUATION OF MULTIPLE‐EXERCISE OPTIONS , 2004 .

[23]  L. Rogers.  Monte Carlo valuation of American options , 2002 .

[24]  L. C. G. Rogers,et al.  Pathwise Stochastic Optimal Control , 2007, SIAM J. Control. Optim..

[25]  Dawn Hunter,et al.  A stochastic mesh method for pricing high-dimensional American options , 2004 .

[26]  M. Talagrand.  Sharper Bounds for Gaussian and Empirical Processes , 1994 .

[27]  Alfredo Ibáñez,et al.  Valuation by Simulation of Contingent Claims with Multiple Early Exercise Opportunities , 2004 .

[28]  E. Giné,et al.  Rates of strong uniform consistency for multivariate kernel density estimators , 2002 .