Search Results for author:
Found 5 papers, 2 papers with code
Differentially Private Topological Data Analysis
We analyze the sensitivity of persistence diagrams in terms of the bottleneck distance, and we show that the commonly used \v{C}ech complex has sensitivity that does not decrease as the sample size $n$ increases.
Differentially Private Bootstrap: New Privacy Analysis and Inference Strategies
Differentially private (DP) mechanisms protect individual-level information by introducing randomness into the statistical analysis procedure.
One Step to Efficient Synthetic Data
We show that under general assumptions, this approach results in a sample with inefficient estimators and whose joint distribution is inconsistent with the true distribution.
Model Selection
Statistics Theory
Cryptography and Security
Computation
Statistics Theory
KNG: The K-Norm Gradient Mechanism
This paper presents a new mechanism for producing sanitized statistical summaries that achieve \emph{differential privacy}, called the \emph{K-Norm Gradient} Mechanism, or KNG.
Benefits and Pitfalls of the Exponential Mechanism with Applications to Hilbert Spaces and Functional PCA
We study its extension to settings with summaries based on infinite dimensional outputs such as with functional data analysis, shape analysis, and nonparametric statistics.
