Discrepancy-based error estimates for Quasi-Monte Carlo. I. General formalism

We show how information on the uniformity properties of a point set employed in numerical multi-dimensional integration can be used to improve the error estimate over the usual Monte Carlo one. We introduce a new measure of (non)uniformity for point sets, and derive explicit expressions for the various entities that enter in such an improved error estimate.

[1]  I. Sobol On the distribution of points in a cube and the approximate evaluation of integrals , 1967 .

[2]  K. F. Roth On irregularities of distribution , 1954 .

[3]  Lauwerens Kuipers,et al.  Uniform distribution of sequences , 1974 .

[4]  J. Halton On the efficiency of certain quasi-random sequences of points in evaluating multi-dimensional integrals , 1960 .

[5]  H. Faure Discrépance de suites associées à un système de numération (en dimension s) , 1982 .

[6]  H. Wozniakowski Average case complexity of multivariate integration , 1991 .

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

[8]  Bennett L. Fox,et al.  Algorithm 647: Implementation and Relative Efficiency of Quasirandom Sequence Generators , 1986, TOMS.

[9]  Petko D. Proinov Discrepancy and integration of continuous functions , 1988 .

[10]  E. Hlawka Funktionen von beschränkter Variatiou in der Theorie der Gleichverteilung , 1961 .

[11]  H. Keng,et al.  Applications of number theory to numerical analysis , 1981 .

[12]  Christoph Schlier,et al.  Monte Carlo integration with quasi-random numbers: some experience , 1991 .

[13]  R. Kleiss Average-case complexity distributions: a generalization of the Woz̀niakowski lemma for multidimensional numerical integration , 1992 .

[14]  Paul Bratley,et al.  Algorithm 659: Implementing Sobol's quasirandom sequence generator , 1988, TOMS.