arXiv Machine Learning
Dimension-Free Private Mean Estimation is Impossible Without the Covariance
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 14
Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
arXiv:2603. 19703v2 Announce Type: replace-cross Abstract: Estimating covariance matrices is fundamental to a wide range of statistical applications.
arXiv Machine Learning
Sep 22
Improved Private Sparse Covariance Estimation with Multiscale Threshold Tests
arXiv:2609. 22783v1 Announce Type: new Abstract: We study differentially private covariance estimation in operator norm for mean-zero sub-Gaussian distributions with unknown covariance support and at most $k$ nonzero entries per row.
arXiv Machine Learning
Oct 28
Gaussian Approximation for Composition and Subsampling of Differentially Private Algorithms
The paper presents a Gaussian approximation for the privacy loss distribution in differentially private stochastic gradient descent (DP‑SGD) when subsampling is used. It shows that, after truncating rare large losses, the privacy loss behaves like a Gaussian with the same mean and variance, up to a small shift that grows only logarithmically with the error tolerance. This leads to tighter variance‑based bounds for subsampled mechanisms, improving upon previous Renyi‑divergence analyses and explaining the effectiveness of the connect‑the‑dots method for random allocation sampling.
arXiv Machine Learning
Oct 5
Differential Privacy of Gradient Descent on Perturbed Objectives
arXiv:2610. 02716v1 Announce Type: new Abstract: Objective perturbation adds a random linear term to a regularized empirical risk and releases the exact perturbed minimizer.
arXiv Statistics ML
Sep 22
Nonparametric spectral density estimation using interactive mechanisms under local differential privacy
arXiv:2504.00919v3 Announce Type: replace-cross Abstract: We study the problem of estimating the spectral density of a centered stationary Gaussian time series under local differential privacy constr...
Hugging Face Trending Papers
Oct 22
Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy
We study learning a discrete distribution under person-level differential privacy in the batched setting. Given $n$ users, each contributing $m$ i.