collaborators

5 papers

stat.ME2026

An online generalization of the (e-)Benjamini-Hochberg procedure

Lasse Fischer, Ziyu Xu, Aaditya Ramdas

In online multiple testing, the hypotheses arrive one by one, and at each time we must immediately reject or accept the current hypothesis solely based on the data and hypotheses o…

stat.ME2026

Bringing Closure to False Discovery Rate Control: A General Principle for Multiple Testing

Ziyu Xu, Aldo Solari, Lasse Fischer +3

We present a novel necessary and sufficient principle for multiple testing methods controlling an expected loss. This principle asserts that every such multiple testing method is a…

stat.ME2025

Active multiple testing with proxy p-values and e-values

Ziyu Xu, Catherine Wang, Larry Wasserman +2

Researchers often lack the resources to test every hypothesis of interest directly or compute test statistics comprehensively, but often possess auxiliary data from which we can co…

stat.ME2025

More powerful multiple testing under dependence via randomization

Ziyu Xu, Aaditya Ramdas

We develop a technique to improve the power of any e-value by a simple randomization involving one independent uniform random variable. Using this framework, we show that two proce…

stat.ME2025

Bringing closure to FDR control: beating the e-Benjamini-Hochberg procedure

Ziyu Xu, Lasse Fischer, Aaditya Ramdas

False discovery rate (FDR) has been a key metric for error control in multiple hypothesis testing, and many methods have developed for FDR control across a diverse cross-section of…