Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kuang, Qi, Gang, Bowen, Xia, Yin
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.29388
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913177536561152
author Kuang, Qi
Gang, Bowen
Xia, Yin
author_facet Kuang, Qi
Gang, Bowen
Xia, Yin
contents This paper develops a framework for differentially private $e$-values under Gaussian differential privacy ($μ$-GDP). We characterize the canonical noise mechanism, establishing that optimal multiplicative perturbation follows a Gaussian distribution. Using this distribution, we derive a globally sharp rejection threshold that strictly improves upon the standard Markov bound. Asymptotic analysis shows that in low-sensitivity regimes, the calibrated private test achieves a net power gain over the non-private baseline. For multiple testing, we introduce a recursive peeling algorithm that adaptively concentrates the privacy budget on the most promising hypotheses. This construction guarantees rigorous $μ$-GDP and yields valid private $e$-values compatible with standard multiple testing procedures. Simulations and a genome-wide association study confirm that the method controls the false discovery rate while improving upon naive all-noisy privatization and recovering power close to non-private benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29388
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Gaussian Differentially Private $e$-values: Construction, Threshold Calibration, and Multiple Testing
Kuang, Qi
Gang, Bowen
Xia, Yin
Methodology
This paper develops a framework for differentially private $e$-values under Gaussian differential privacy ($μ$-GDP). We characterize the canonical noise mechanism, establishing that optimal multiplicative perturbation follows a Gaussian distribution. Using this distribution, we derive a globally sharp rejection threshold that strictly improves upon the standard Markov bound. Asymptotic analysis shows that in low-sensitivity regimes, the calibrated private test achieves a net power gain over the non-private baseline. For multiple testing, we introduce a recursive peeling algorithm that adaptively concentrates the privacy budget on the most promising hypotheses. This construction guarantees rigorous $μ$-GDP and yields valid private $e$-values compatible with standard multiple testing procedures. Simulations and a genome-wide association study confirm that the method controls the false discovery rate while improving upon naive all-noisy privatization and recovering power close to non-private benchmarks.
title Gaussian Differentially Private $e$-values: Construction, Threshold Calibration, and Multiple Testing
topic Methodology
url https://arxiv.org/abs/2605.29388