uniform.optim: Optimize a design based on the wrap-around discrepancy

In SFDesign: Space-Filling Designs

Optimize a design based on the wrap-around discrepancy

Description

This function optimizes a design through continuous optimization of the wrap-around discrepancy.

Usage

uniform.optim(D.ini, iteration = 10)

Arguments

D.ini	the initial design.
iteration	number iterations for LBFGS.

Details

uniform.optim optimizes a design through continuous optimization of the wrap-around discrepancy (see uniform.crit) by L-BFGS-B algorithm (Liu and Nocedal 1989).

Value

design	optimized design.
D.ini	initial design.

References

Liu, D. C., & Nocedal, J. (1989). On the limited memory BFGS method for large scale optimization. Mathematical programming, 45(1), 503-528.

Examples

n = 20
p = 3
D = uniformLHD(n, p)$design
D = uniform.optim(D)$design

SFDesign documentation built on June 22, 2025, 1:06 a.m.