中文
相关论文

相关论文: Re-Analyze Gauss: Bounds for Private Matrix Approx…

200 篇论文

We consider the problem of approximating a $d \times d$ covariance matrix $M$ with a rank-$k$ matrix under $(\varepsilon,\delta)$-differential privacy. We present and analyze a complex variant of the Gaussian mechanism and obtain upper…

数据结构与算法 · 计算机科学 2025-02-12 Oren Mangoubi , Nisheeth K. Vishnoi

We consider the problem of approximating a $d \times d$ covariance matrix $M$ with a rank-$k$ matrix under $(\varepsilon,\delta)$-differential privacy. We present and analyze a complex variant of the Gaussian mechanism and show that the…

数据结构与算法 · 计算机科学 2023-06-30 Oren Mangoubi , Nisheeth K. Vishnoi

Given a matrix $A \in \mathbb{R}^{m\times d}$ with singular values $\sigma_1\geq \cdots \geq \sigma_d$, and a random matrix $G \in \mathbb{R}^{m\times d}$ with iid $N(0,T)$ entries for some $T>0$, we derive new bounds on the Frobenius…

统计理论 · 数学 2024-06-05 Peiyao Lai , Oren Mangoubi

We prove new lower bounds for statistical estimation tasks under the constraint of $(\varepsilon, \delta)$-differential privacy. First, we provide tight lower bounds for private covariance estimation of Gaussian distributions. We show that…

数据结构与算法 · 计算机科学 2023-03-29 Gautam Kamath , Argyris Mouzakis , Vikrant Singhal

We offer an alternative viewpoint on Dyson's original paper regarding the application of Brownian motion to random matrix theory (RMT). In particular we show how one may use the same approach in order to study the stochastic motion in the…

数学物理 · 物理学 2015-03-24 Christopher H. Joyner , Uzy Smilansky

The Gaussian mechanism is an essential building block used in multitude of differentially private data analysis algorithms. In this paper we revisit the Gaussian mechanism and show that the original analysis has several important…

机器学习 · 计算机科学 2018-06-08 Borja Balle , Yu-Xiang Wang

The wide deployment of machine learning in recent years gives rise to a great demand for large-scale and high-dimensional data, for which the privacy raises serious concern. Differential privacy (DP) mechanisms are conventionally developed…

密码学与安全 · 计算机科学 2021-05-03 Jungang Yang , Liyao Xiang , Weiting Li , Wei Liu , Xinbing Wang

Consider the following optimization problem: Given $n \times n$ matrices $A$ and $\Lambda$, maximize $\langle A, U\Lambda U^*\rangle$ where $U$ varies over the unitary group $\mathrm{U}(n)$. This problem seeks to approximate $A$ by a matrix…

数据结构与算法 · 计算机科学 2022-07-08 Oren Mangoubi , Yikai Wu , Satyen Kale , Abhradeep Guha Thakurta , Nisheeth K. Vishnoi

A central challenge in machine learning is to understand how noise or measurement errors affect low-rank approximations, particularly in the spectral norm. This question is especially important in differentially private low-rank…

机器学习 · 计算机科学 2025-10-30 Phuc Tran , Nisheeth K. Vishnoi , Van H. Vu

Since the introduction of Dyson's Brownian motion in early 1960's, there have been a lot of developments in the investigation of stochastic processes on the space of Hermitian matrices. Their properties, especially, the properties of their…

概率论 · 数学 2021-09-28 Jian Song , Jianfeng Yao , Wangjun Yuan

We establish a correspondence between the evolution of the distribution of eigenvalues of a $N\times N$ matrix subject to a random Gaussian perturbing matrix, and a Fokker-Planck equation postulated by Dyson. Within this model, we prove the…

凝聚态物理 · 物理学 2009-10-22 Onuttom Narayan , B. Sriram Shastry

The Gaussian mechanism is one differential privacy mechanism commonly used to protect numerical data. However, it may be ill-suited to some applications because it has unbounded support and thus can produce invalid numerical answers to…

密码学与安全 · 计算机科学 2022-12-01 Bo Chen , Matthew Hale

We characterize the minimum noise amplitude and power for noise-adding mechanisms in $(\epsilon, \delta)$-differential privacy for single real-valued query function. We derive new lower bounds using the duality of linear programming, and…

密码学与安全 · 计算机科学 2019-02-06 Quan Geng , Wei Ding , Ruiqi Guo , Sanjiv Kumar

The Gaussian Mechanism (GM), which consists in adding Gaussian noise to a vector-valued query before releasing it, is a standard privacy protection mechanism. In particular, given that the query respects some L2 sensitivity property (the L2…

机器学习 · 计算机科学 2024-03-20 Hadrien Hendrikx , Paul Mangold , Aurélien Bellet

There is a disconnect between how researchers and practitioners handle privacy-utility tradeoffs. Researchers primarily operate from a privacy first perspective, setting strict privacy requirements and minimizing risk subject to these…

机器学习 · 计算机科学 2023-11-14 Justin Whitehouse , Zhiwei Steven Wu , Aaditya Ramdas , Ryan Rogers

Due to their importance in both data analysis and numerical algorithms, low rank approximations have recently been widely studied. They enable the handling of very large matrices. Tight error bounds for the computationally efficient…

数值分析 · 数学 2023-04-06 Frank de Hoog , Markus Hegland

We study differentially private (DP) training with Muon, a matrix-valued optimizer that updates hidden-layer weights using momentum followed by Newton--Schulz orthogonalization. While DP-SGD is well understood, the interaction between…

机器学习 · 计算机科学 2026-05-14 Jihwan Kim , Chenglin Fan

We study the problem of privately estimating the parameters of $d$-dimensional Gaussian Mixture Models (GMMs) with $k$ components. For this, we develop a technique to reduce the problem to its non-private counterpart. This allows us to…

机器学习 · 统计学 2023-06-09 Jamil Arbas , Hassan Ashtiani , Christopher Liaw

We consider a toy model for the study of monitored dynamics in a many-body quantum systems. We study the stochastic Schrodinger equation resulting from the continuous monitoring with a rate $\Gamma$ of a random hermitian operator chosen at…

统计力学 · 物理学 2024-07-02 Federico Gerbino , Pierre Le Doussal , Guido Giachetti , Andrea De Luca

The covariance matrix plays a fundamental role in the analysis of high-dimensional data. This paper studies minimax and adaptive estimation of high-dimensional bandable covariance matrices under differential privacy constraints. We propose…

统计理论 · 数学 2026-03-23 T. Tony Cai , Yicheng Li
‹ 上一页 1 2 3 10 下一页 ›