Back to Paper
cs.CRcs.DScs.ITcs.LGmath.ST
Local ID: 2605.28952v2
AI Summary: gemma4:e4b
Optimal Rates for Differentially Private Hypothesis Testing with E-values
By Ben Jacobsen, Tomas Gonzalez, Gavin Brown, Kassem Fawaz, Aaditya Ramdas
Revision History Timeline
v15/27/2026
5/27/2026
“28 pages, 2 figures”
v25/29/2026
5/29/2026
“Corrected typos; updated references; generalized proposition 3.1”
★ Version indexed in ExplorerComparing v1 vs v2
Green = Added • Red = Removed
Title Comparison
Optimal Rates for Differentially Private Hypothesis Testing with E-values
Authors Comparison
Removed:Tomas Gonzales
Added:Tomas Gonzalez
Unchanged:Ben Jacobsen, Gavin Brown, Kassem Fawaz, Aaditya Ramdas
v1 Comment
“28 pages, 2 figures”
v2 Comment
“Corrected typos; updated references; generalized proposition 3.1”
Abstract Word Diff
E-values have attracted considerable interest in recent years as flexible tools for enabling anytime-valid and adaptive data analysis. Hypothesis testing is at the core of many of these applications, which can often involve private or sensitive data. In this work, we answer a simple but important question: given two distributions $\mathbb{P}$ and $\mathbb{Q}$, what is the maximum achievable e-power when testing $X\sim \mathbb{P}^n$ against $X\sim\mathbb{Q}^n$ with e-values that satisfy $\varepsilon$-differential privacy? We characterize the optimal rate for this problem and provide an algorithm which matches it exactly. In the sequential setting, when observations arrive one-by-one and the analyst chooses when to halt, we give matching upper and lower bounds on the stopping times of any private e-process. Numerical experiments confirm the practicality of our algorithms, which require less data than the recently proposed DP-SPRT across a range of sequential testing problems and privacy levels.