中文
相关论文

相关论文: Sample-Efficient Private Learning of Mixtures of G…

200 篇论文

We study the problem of estimating mixtures of Gaussians under the constraint of differential privacy (DP). Our main result is that $\text{poly}(k,d,1/\alpha,1/\varepsilon,\log(1/\delta))$ samples are sufficient to estimate a mixture of $k$…

机器学习 · 统计学 2024-04-24 Mohammad Afzali , Hassan Ashtiani , Christopher Liaw

We consider the problem of learning mixtures of Gaussians under the constraint of approximate differential privacy. We prove that $\widetilde{O}(k^2 d \log^{3/2}(1/\delta) / \alpha^2 \varepsilon)$ samples are sufficient to learn a mixture…

机器学习 · 计算机科学 2021-06-07 Ishaq Aden-Ali , Hassan Ashtiani , Christopher Liaw

We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance. This improves both the known upper…

机器学习 · 计算机科学 2020-07-23 Hassan Ashtiani , Shai Ben-David , Nick Harvey , Christopher Liaw , Abbas Mehrabian , Yaniv Plan

We provide sample complexity upper bounds for agnostically learning multivariate Gaussians under the constraint of approximate differential privacy. These are the first finite sample upper bounds for general Gaussians which do not impose…

机器学习 · 统计学 2020-10-21 Ishaq Aden-Ali , Hassan Ashtiani , Gautam Kamath

Learning the parameters of Gaussian mixture models is a fundamental and widely studied problem with numerous applications. In this work, we give new algorithms for learning the parameters of a high-dimensional, well separated, Gaussian…

数据结构与算法 · 计算机科学 2019-10-17 Gautam Kamath , Or Sheffet , Vikrant Singhal , Jonathan Ullman

Learning a Gaussian mixture model (GMM) is a fundamental problem in machine learning, learning theory, and statistics. One notion of learning a GMM is proper learning: here, the goal is to find a mixture of $k$ Gaussians $\mathcal{M}$ that…

数据结构与算法 · 计算机科学 2015-06-04 Jerry Li , Ludwig Schmidt

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 present a fairly general framework for reducing $(\varepsilon, \delta)$ differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and…

机器学习 · 统计学 2022-06-23 Hassan Ashtiani , Christopher Liaw

In this paper we present a method for learning the parameters of a mixture of $k$ identical spherical Gaussians in $n$-dimensional space with an arbitrarily small separation between the components. Our algorithm is polynomial in all…

机器学习 · 计算机科学 2010-05-14 Mikhail Belkin , Kaushik Sinha

We consider the problem of efficiently learning mixtures of a large number of spherical Gaussians, when the components of the mixture are well separated. In the most basic form of this problem, we are given samples from a uniform mixture of…

数据结构与算法 · 计算机科学 2017-11-01 Oded Regev , Aravindan Vijayaraghavan

Efficiently learning mixture of Gaussians is a fundamental problem in statistics and learning theory. Given samples coming from a random one out of k Gaussian distributions in Rn, the learning problem asks to estimate the means and the…

机器学习 · 计算机科学 2015-03-11 Rong Ge , Qingqing Huang , Sham M. Kakade

We study the problem of learning mixtures of $k$ Gaussians in $d$ dimensions. We make no separation assumptions on the underlying mixture components: we only require that the covariance matrices have bounded condition number and that the…

数据结构与算法 · 计算机科学 2024-11-20 Sitan Chen , Vasilis Kontonis , Kulin Shah

We consider the problem of identifying the parameters of an unknown mixture of two arbitrary $d$-dimensional gaussians from a sequence of independent random samples. Our main results are upper and lower bounds giving a computationally…

机器学习 · 计算机科学 2015-05-19 Moritz Hardt , Eric Price

Suppose that we are given independent, identically distributed samples $x_l$ from a mixture $\mu$ of no more than $k$ of $d$-dimensional spherical gaussian distributions $\mu_i$ with variance $1$, such that the minimum $\ell_2$ distance…

数据结构与算法 · 计算机科学 2025-09-10 Somnath Chakraborty , Hariharan Narayanan

We initiate the study of differentially private (DP) estimation with access to a small amount of public data. For private estimation of d-dimensional Gaussians, we assume that the public data comes from a Gaussian that may have vanishing…

机器学习 · 计算机科学 2023-04-07 Alex Bie , Gautam Kamath , Vikrant Singhal

In this work, we give efficient algorithms for privately estimating a Gaussian distribution in both pure and approximate differential privacy (DP) models with optimal dependence on the dimension in the sample complexity. In the pure DP…

数据结构与算法 · 计算机科学 2023-06-02 Daniel Alabi , Pravesh K. Kothari , Pranay Tankala , Prayaag Venkat , Fred Zhang

We study the problem of private distribution learning with access to public data. In this setup, which we refer to as public-private learning, the learner is given public and private samples drawn from an unknown distribution $p$ belonging…

机器学习 · 计算机科学 2023-08-16 Shai Ben-David , Alex Bie , Clément L. Canonne , Gautam Kamath , Vikrant Singhal

We present novel, computationally efficient, and differentially private algorithms for two fundamental high-dimensional learning problems: learning a multivariate Gaussian and learning a product distribution over the Boolean hypercube in…

数据结构与算法 · 计算机科学 2019-05-31 Gautam Kamath , Jerry Li , Vikrant Singhal , Jonathan Ullman

Given data drawn from a mixture of multivariate Gaussians, a basic problem is to accurately estimate the mixture parameters. We give an algorithm for this problem that has a running time, and data requirement polynomial in the dimension and…

机器学习 · 计算机科学 2010-04-27 Ankur Moitra , Gregory Valiant

One of the most popular algorithms for clustering in Euclidean space is the $k$-means algorithm; $k$-means is difficult to analyze mathematically, and few theoretical guarantees are known about it, particularly when the data is {\em…

机器学习 · 计算机科学 2009-12-02 Kamalika Chaudhuri , Sanjoy Dasgupta , Andrea Vattani
‹ 上一页 1 2 3 10 下一页 ›