Fast confidence bounds for the false discovery proportion over a path of hypotheses

TL;DR

This paper introduces a fast algorithm for computing entire curves of post hoc bounds on the False Discovery Proportion over a sequence of hypotheses, significantly reducing computational complexity.

Contribution

The paper presents a novel algorithm that efficiently computes bounds on the false discovery proportion along a path of hypotheses with a forest-structured reference family.

Findings

Algorithm reduces complexity from O(|K|m^2) to O(|K|m)

Enables fast computation of FDP bounds over hypothesis paths

Applicable to forest-structured reference families

Abstract

This paper presents a new algorithm (and an additional trick) that allows to compute fastly an entire curve of post hoc bounds for the False Discovery Proportion when the underlying bound $V^*\_{\mathfrak{R}}$ construction is based on a reference family $\mathfrak{R}$ with a forest structure {\`a} la Durand et al. (2020). By an entire curve, we mean the values $V^*\_{\mathfrak{R}}(S\_1),\dotsc,V^*\_{\mathfrak{R}}(S\_m)$ computed on a path of increasing selection sets $S\_1\subsetneq\dotsb\subsetneq S\_m$, $|S\_t|=t$. The new algorithm leverages the fact that going from $S\_t$ to $S\_{t+1}$ is done by adding only one hypothesis. Compared to a more naive approach, the new algorithm has a complexity in $O(|\mathcal K|m)$ instead of $O(|\mathcal K|m^2)$, where $|\mathcal K|$ is the cardinality of the family.