Monte Carlo Algorithms for Optimal Stopping and Statistical Learning
نویسنده
چکیده
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 obtained by Clément, Lamberton and Protter (2002).
منابع مشابه
Evaluating Performance of Algorithms in Lung IMRT: A Comparison of Monte Carlo, Pencil Beam, Superposition, Fast Superposition and Convolution Algorithms
Background: Inclusion of inhomogeneity corrections in intensity modulated small fields always makes conformal irradiation of lung tumor very complicated in accurate dose delivery.Objective: In the present study, the performance of five algorithms via Monte Carlo, Pencil Beam, Convolution, Fast Superposition and Superposition were evaluated in lung cancer Intensity Modulated Radiotherapy plannin...
متن کاملOptimal Monte Carlo Estimation of Belief Network Inference
We present two Monte Carlo sampling algo rithms for probabilistic inference that guarantee polynomial-time convergence for a larger class of network than current sampling algorithms pro vide. These new methods are variants of the known likelihood weighting algorithm. We use of recent advances in the theory of optimal stopping rules for Monte Carlo simulation to obtain an inference approximati...
متن کاملStopping Rules for a Class of Sampling-Based Stochastic Programming Algorithms
Decomposition and Monte Carlo sampling-based algorithms hold much promise for solving stochastic programs with many scenarios. A critical component of such algorithms is a stopping criterion to ensure the quality of the solution. In this paper, we develop a stopping rule theory for a class of algorithms that estimate bounds on the optimal objective function value by sampling. We provide rules f...
متن کاملOn the optimal number of clusters in histogram clustering
Unsupervised learning algorithms are designed to extract structure from data samples. The quality of a structure is measured by a cost function which is usually minimized to infer optimal parameters characterizing the hidden structure in the data. Reliable and robust inference requires a guarantee that extracted structures are typical for the data source, i.e., similar structures have to be ext...
متن کاملStochastic Programming by Monte Carlo Simulation Methods
We consider in this paper stochastic programming problems which can be formulated as an optimization problem of an expected value function subject to deterministic constraints. We discuss a Monte Carlo simulation approach based on sample average approximations to a numerical solution of such problems. In particular, we give a survey of a statistical inference of the sample average estimators of...
متن کامل