Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches
1 version
AM
Audra McMillan
cs.CRcs.LGcs.DSstat.MLmath.STstat.MEstat.THcs.ITmath.ITcs.DB
On Valency
published · living versionsPreprints & journals
20 papers in the corpus · 2016–2026Understanding Private Evolution as Learning-Augmented Clustering
0 citations
Local Pan-Privacy for Federated Analytics
0 citations
Private Selection with Heterogeneous Sensitivities
0 citations
Instance-Optimal Private Density Estimation in the Wasserstein Distance
1 citation
Mean Estimation with User-level Privacy under Data Heterogeneity
12 citations
Samplable Anonymous Aggregation for Private Federated Data Analysis
10 citations
Differentially Private Heavy Hitter Detection using Federated Analytics
10 citations
Private Federated Statistics in an Interactive Setting
3 citations
Instance-Optimal Differentially Private Estimation
0 citations
Stronger Privacy Amplification by Shuffling for Rényi and Approximate Differential Privacy
0 citations
Non-parametric Differentially Private Confidence Intervals for the Median
9 citations
Hiding Among the Clones: A Simple and Nearly Optimal Analysis of Privacy Amplification by Shuffling
86 citations
Controlling Privacy Loss in Sampling Schemes: an Analysis of Stratified and Cluster Sampling
10 citations
Differentially Private Simple Linear Regression
15 citations
Private Identity Testing for High-Dimensional Distributions
15 citations
The Structure of Optimal Private Tests for Simple Hypotheses
53 citations
Property Testing for Differential Privacy
19 citations
Online Learning via the Differential Privacy Lens
8 citations
Local Differential Privacy for Physical Sensor Data and Sparse Recovery
6 citations
When is Nontrivial Estimation Possible for Graphons and Stochastic Block Models?
3 citations
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.