no code implementations • 23 Jan 2025 • Kelly Ramsay, Dylan Spicker
We consider the modified winsorized mean as the aggregator in subsample-and-aggregate, deriving a finite sample deviations bound for a subsample-and-aggregate estimate generated with the new aggregator.
1 code implementation • 12 Dec 2023 • Kelly Ramsay, Dylan Spicker
Under general conditions on the input parameters and the population measure, (e. g. we do not assume any moment bounds), we quantify the probability the test in PTR fails, as well as the cost of privacy via finite sample deviation bounds.
1 code implementation • 12 Oct 2022 • Kelly Ramsay, Aukosh Jagannath, Shoja'eddin Chenouri
We develop novel finite-sample performance guarantees for differentially private multivariate depth-based medians, which are essentially sharp.
