Differentially Private E-Values

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Csillag, Daniel, Mesquita, Diego
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908604840280064
author Csillag, Daniel
Mesquita, Diego
author_facet Csillag, Daniel
Mesquita, Diego
contents E-values have gained prominence as flexible tools for statistical inference and risk control, enabling anytime- and post-hoc-valid procedures under minimal assumptions. However, many real-world applications fundamentally rely on sensitive data, which can be leaked through e-values. To ensure their safe release, we propose a general framework to transform non-private e-values into differentially private ones. Towards this end, we develop a novel biased multiplicative noise mechanism that ensures our e-values remain statistically valid. We show that our differentially private e-values attain strong statistical power, and are asymptotically as powerful as their non-private counterparts. Experiments across online risk monitoring, private healthcare, and conformal e-prediction demonstrate our approach's effectiveness and illustrate its broad applicability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18654
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Differentially Private E-Values
Csillag, Daniel
Mesquita, Diego
Methodology
Cryptography and Security
Machine Learning
E-values have gained prominence as flexible tools for statistical inference and risk control, enabling anytime- and post-hoc-valid procedures under minimal assumptions. However, many real-world applications fundamentally rely on sensitive data, which can be leaked through e-values. To ensure their safe release, we propose a general framework to transform non-private e-values into differentially private ones. Towards this end, we develop a novel biased multiplicative noise mechanism that ensures our e-values remain statistically valid. We show that our differentially private e-values attain strong statistical power, and are asymptotically as powerful as their non-private counterparts. Experiments across online risk monitoring, private healthcare, and conformal e-prediction demonstrate our approach's effectiveness and illustrate its broad applicability.
title Differentially Private E-Values
topic Methodology
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2510.18654