On Large-Scale Multiple Testing Over Networks: An Asymptotic Approach

arXiv:2211.16059v4 Announce Type: replace-cross
Abstract: This work concerns developing communication- and computation-efficient methods for large-scale multiple testing over networks, which is of interest to many practical applications. We take an asymptotic approach and propose two methods, proportion-matching and greedy aggregation, tailored to distributed settings. The proportion-matching method achieves the global BH performance yet only requires a one-shot communication of the (estimated) proportion of true null hypotheses as well as the number of p-values at each node. By focusing on the …

abstract aggregation applications arxiv communication computation concerns cs.lg cs.sy distributed eess.sp eess.sy global multiple networks practical scale stat.me testing type work