3 papers
cs.LG2025
Empirical Privacy Variance
Yuzheng Hu, Fan Wu, Ruicheng Xian +5
We propose the notion of empirical privacy variance and study it in the context of differentially private fine-tuning of language models. Specifically, we show that models calibrat…
cs.LG2025
Tukey Depth Mechanisms for Practical Private Mean Estimation
Gavin Brown, Lydia Zakynthinou
Mean estimation is a fundamental task in statistics and a focus within differentially private statistical estimation. While univariate methods based on the Gaussian mechanism are w…
cs.LG2024
Dimension-free Private Mean Estimation for Anisotropic Distributions
Yuval Dagan, Michael I. Jordan, Xuelin Yang +2
We present differentially private algorithms for high-dimensional mean estimation. Previous private estimators on distributions over suffer from a curse of dimension…