Expected $L_2-$discrepancy bound for a class of new stratified sampling models
Statistics Theory
2022-04-20 v1 Probability
Statistics Theory
Abstract
We introduce a class of convex equivolume partitions. Expected discrepancy are discussed under these partitions. There are two main results. First, under this kind of partitions, we generate random point sets with smaller expected discrepancy than classical jittered sampling for the same sampling number. Second, an explicit expected discrepancy upper bound under this kind of partitions is also given. Further, among these new partitions, there is optimal expected discrepancy upper bound.
Cite
@article{arxiv.2204.08752,
title = {Expected $L_2-$discrepancy bound for a class of new stratified sampling models},
author = {Jun Xian and Xiaoda Xu},
journal= {arXiv preprint arXiv:2204.08752},
year = {2022}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2203.01288