Global Stochastic Optimization with Low-Dispersion Point Sets

This study concerns a generic model-free stochastic optimization problem requiring the minimization of a risk function defined on a given bounded domain in a Euclidean space. Smoothness assumptions regarding the risk function are hypothesized, and members of the underlying space of probabilities are presumed subject to a large deviation principle; however, the risk function may well be nonconvex and multimodal. A general approach to finding the risk minimizer on the basis of decision/observation pairs is proposed. It consists of repeatedly observing pairs over a collection of design points. Principles are derived for choosing the number of these design points on the basis of an observation budget, and for allocating the observations between these points in both prescheduled and adaptive settings. On the basis of these principles, large-deviation type bounds of the minimizer in terms of sample size are established.

[1]  J. Spall Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[2]  Paul Deheuvels,et al.  Strong bounds for multidimensional spacings , 1983 .

[3]  Harald Niederreiter,et al.  Random number generation and Quasi-Monte Carlo methods , 1992, CBMS-NSF regional conference series in applied mathematics.

[4]  A. Tamhane Design and Analysis of Experiments for Statistical Selection, Screening, and Multiple Comparisons , 1995 .

[5]  R. Deal Simulation Modeling and Analysis (2nd Ed.) , 1994 .

[6]  Averill M. Law,et al.  Simulation Modeling and Analysis , 1982 .

[7]  Feller William,et al.  An Introduction To Probability Theory And Its Applications , 1950 .

[8]  R. Ellis,et al.  Entropy, large deviations, and statistical mechanics , 1985 .

[9]  H. Kushner,et al.  Stochastic Approximation Methods for Systems Over an InfiniteHorizon , 1996 .

[10]  H. Muller Kernel estimators of zeros and of location and size of extrema of regression functions , 1985 .

[11]  S. Yakowitz,et al.  Machine learning and nonparametric bandit theory , 1995, IEEE Trans. Autom. Control..

[12]  Peter W. Glynn,et al.  Likelihood ratio gradient estimation for stochastic systems , 1990, CACM.

[13]  Hans-Georg Müller,et al.  Adaptive Nonparametric Peak Estimation , 1989 .

[14]  P. L’Ecuyer Two approaches for estimating the gradient in functional form , 1993, WSC '93.

[15]  A. G. Sukharev Optimal strategies of the search for an extremum , 1971 .

[16]  A. Blokhuis SPHERE PACKINGS, LATTICES AND GROUPS (Grundlehren der mathematischen Wissenschaften 290) , 1989 .

[17]  W. Härdle Applied Nonparametric Regression , 1992 .

[18]  Carlos S. Kubrusly,et al.  Stochastic approximation algorithms and applications , 1973, CDC 1973.

[19]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1967 .

[20]  Barry L. Nelson,et al.  Two-Stage Multiple Comparisons with the Best for Computer Simulation , 1995, Oper. Res..

[21]  Charles Leake,et al.  Discrete Event Systems: Sensitivity Analysis and Stochastic Optimization by the Score Function Method , 1994 .

[22]  Pierre L'Ecuyer,et al.  An overview of derivative estimation , 1991, 1991 Winter Simulation Conference Proceedings..

[23]  Jason H. Goodfriend,et al.  Discrete Event Systems: Sensitivity Analysis and Stochastic Optimization by the Score Function Method , 1995 .

[24]  W. Fischer,et al.  Sphere Packings, Lattices and Groups , 1990 .

[25]  W. Härdle Applied Nonparametric Regression , 1991 .

[26]  Harold J. Kushner,et al.  Stochastic Approximation Algorithms and Applications , 1997, Applications of Mathematics.

[27]  Pierre Priouret,et al.  Adaptive Algorithms and Stochastic Approximations , 1990, Applications of Mathematics.

[28]  Harold J. Kushner,et al.  wchastic. approximation methods for constrained and unconstrained systems , 1978 .

[29]  A. Shiryayev On Sums of Independent Random Variables , 1992 .

[30]  Paul Glasserman,et al.  Gradient Estimation Via Perturbation Analysis , 1990 .

[31]  Stochastic approximation of global minimum points , 1994 .

[32]  S. Yakowitz A globally convergent stochastic approximation , 1993 .

[33]  Pierre L'Ecuyer,et al.  On the Convergence Rates of IPA and FDC Derivative Estimators , 1990, Oper. Res..

[34]  Yu-Chi Ho,et al.  Functional Estimation with Respect to a Threshold Parametervia Dynamic Split-and-Merge , 1997 .

[35]  H. Robbins Some aspects of the sequential design of experiments , 1952 .

[36]  Gang George Yin,et al.  Budget-Dependent Convergence Rate of Stochastic Approximation , 1995, SIAM J. Optim..

[37]  Prakasa Rao Nonparametric functional estimation , 1983 .

[38]  S. Yakowitz,et al.  Methods and theory for off-line machine learning , 1995, IEEE Trans. Autom. Control..

[39]  Pierre L'Ecuyer,et al.  Functional Estimation with Respect to a Threshold Parameter via Dynamic Split-and-Merge , 1997, Discret. Event Dyn. Syst..

[40]  Yu-Chi Ho,et al.  Ordinal optimization approach to rare event probability problems , 1995, Discret. Event Dyn. Syst..