paper-with-me

홈 › Papers

Differentially Private Covariance Revisited

2022-05-28 · Wei Dong, Yuting Liang, Ke Yi

In this paper, we present two new algorithms for covariance estimation under concentrated differential privacy (zCDP). The first algorithm achieves a Frobenius error of $\tilde{O}(d^{1/4}\sqrt{\mathrm{tr}}/\sqrt{n} + \sqrt{d}/n)$, where $\mathrm{tr}$ is the trace of the covariance matrix. By taking $\mathrm{tr}=1$, this also implies a worst-case error bound of $\tilde{O}(d^{1/4}/\sqrt{n})$, which improves the standard Gaussian mechanism's $\tilde{O}(d/n)$ for the regime $d>\widetilde{\Omega}(n^{2/3})$. Our second algorithm offers a tail-sensitive bound that could be much better on skewed data. The corresponding algorithms are also simple and efficient. Experimental results show that they offer significant improvements over prior work.

📄 PDF Abstract BibTeX arXiv:2205.14324

Code (2)

hkustdb/privatecovariance 공식 구현 pytorch
opencode2022/privatecovariance 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Differentially Private Matrix Completion Revisited

2017-12-28 · ICML 2018 7 · Prateek Jain, Om Thakkar, Abhradeep Thakurta

We provide the first provably joint differentially private algorithm with formal utility guarantees for the problem of user-level privacy-preserving collaborative filtering. Our algorithm is based on the Frank-Wolfe meth…

Collaborative FilteringMatrix CompletionPrivacy Preserving

Differentially Private Precision Matrix Estimation

2019-09-06 · Wenqing Su, Xiao Guo, Hai Zhang

In this paper, we study the problem of precision matrix estimation when the dataset contains sensitive information. In the differential privacy framework, we develop a differentially private ridge estimator by perturbing…

Differentially Private Covariance Estimation

2019-12-01 · NeurIPS 2019 12 · Kareem Amin, Travis Dick, Alex Kulesza, Andres Munoz 외

The covariance matrix of a dataset is a fundamental statistic that can be used for calculating optimum regression weights as well as in many other learning and data analysis settings. For datasets containing private user…

Covariance-Aware Private Mean Estimation Without Private Covariance Estimation

2021-06-24 · NeurIPS 2021 12 · Gavin Brown, Marco Gaboardi, Adam Smith, Jonathan Ullman 외

We present two sample-efficient differentially private mean estimators for $d$-dimensional (sub)Gaussian distributions with unknown covariance. Informally, given $n \gtrsim d/\alpha^2$ samples from such a distribution wi…

Optimal Differentially Private PCA and Estimation for Spiked Covariance Matrices

2024-01-08 · T. Tony Cai, Dong Xia, Mengyue Zha

Estimating a covariance matrix and its associated principal components is a fundamental problem in contemporary statistics. While optimal estimation procedures have been developed with well-understood properties, the inc…

valid