中文
相关论文

相关论文: Maximum Number of Modes of Gaussian Mixtures

200 篇论文

We show, by an explicit construction, that a mixture of univariate Gaussian densities with variance $1$ and means in $[-A,A]$ can have $\Omega(A^2)$ modes. This disproves a recent conjecture of Dytso, Yagli, Poor and Shamai \cite{DYPS20}…

统计理论 · 数学 2020-10-23 Navin Kashyap , Manjunath Krishnapur

We derive explicit upper bounds for the number of nondegenerate critical points of a $k$-component Gaussian mixture density in $\mathbb{R}^d$, and the number of modes when the modal set is finite, together with lower bounds. By normalizing…

统计理论 · 数学 2026-05-18 Hien Duy Nguyen

We present an optimal mass transport framework on the space of Gaussian mixture models, which are widely used in statistical inference. Our method leads to a natural way to compare, interpolate and average Gaussian mixture models.…

概率论 · 数学 2018-02-01 Yongxin Chen , Tryphon T. Georgiou , Allen Tannenbaum

In this paper, we study the problem of learning one-dimensional Gaussian mixture models (GMMs) with a specific focus on estimating both the model order and the mixing distribution from independent and identically distributed (i.i.d.)…

机器学习 · 统计学 2026-02-24 Xinyu Liu , Hai Zhang

Density estimation is an interdisciplinary topic at the intersection of statistics, theoretical computer science and machine learning. We review some old and new techniques for bounding the sample complexity of estimating densities of…

统计理论 · 数学 2018-02-23 Hassan Ashtiani , Abbas Mehrabian

We present a series of closed-form maximum entropy upper bounds for the differential entropy of a continuous univariate random variable and study the properties of that series. We then show how to use those generic bounds for upper bounding…

信息论 · 计算机科学 2026-01-06 Frank Nielsen , Richard Nock

We consider estimating the parameters of a Gaussian mixture density with a given number of components best representing a given set of weighted samples. We adopt a density interpretation of the samples by viewing them as a discrete Dirac…

机器学习 · 统计学 2025-04-03 Daniel Frisch , Uwe D. Hanebeck

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

Gaussian mixture models are central to classical statistics, widely used in the information sciences, and have a rich mathematical structure. We examine their maximum likelihood estimates through the lens of algebraic statistics. The MLE is…

统计理论 · 数学 2019-04-19 Carlos Améndola , Mathias Drton , Bernd Sturmfels

An often-cited fact regarding mixing or mixture distributions is that their density functions are able to approximate the density function of any unknown distribution to arbitrary degrees of accuracy, provided that the mixing or mixture…

其他统计学 · 统计学 2018-03-05 Hien D. Nguyen , Geoffrey J. McLachlan

The method of moments is a classical statistical technique for density estimation that solves a system of moment equations to estimate the parameters of an unknown distribution. A fundamental question critical to understanding…

统计方法学 · 统计学 2024-06-12 Julia Lindberg , Carlos Améndola , Jose Israel Rodriguez

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

We study Bayesian estimation of finite mixture models in a general setup where the number of components is unknown and allowed to grow with the sample size. An assumption on growing number of components is a natural one as the degree of…

统计理论 · 数学 2022-03-18 Ilsang Ohn , Lizhen Lin

Mixture models, such as Gaussian mixture models, are widely used in machine learning to represent complex data distributions. A key challenge, especially in high-dimensional settings, is to determine the mixture order and estimate the…

最优化与控制 · 数学 2025-09-30 Srećko Đurašinović , Jean-Bernard Lasserre , Victor Magron

We study the problem of learning mixtures of Gaussians with approximate differential privacy. We prove that roughly $kd^2 + k^{1.5} d^{1.75} + k^2 d$ samples suffice to learn a mixture of $k$ arbitrary $d$-dimensional Gaussians up to low…

机器学习 · 计算机科学 2024-11-05 Hassan Ashtiani , Mahbod Majid , Shyam Narayanan

This paper studies the optimal rate of estimation in a finite Gaussian location mixture model in high dimensions without separation conditions. We assume that the number of components $k$ is bounded and that the centers lie in a ball of…

统计理论 · 数学 2021-07-27 Natalie Doss , Yihong Wu , Pengkun Yang , Harrison H. Zhou

Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory. While the total variation distance appears naturally in the sample complexity of distribution learning, it is analytically…

概率论 · 数学 2022-03-11 Sami Davies , Arya Mazumdar , Soumyabrata Pal , Cyrus Rashtchian

Machine learning systems operate under the assumption that training and test data are sampled from a fixed probability distribution. However, this assumptions is rarely verified in practice, as the conditions upon which data was acquired…

机器学习 · 计算机科学 2025-07-09 Eduardo Fernandes Montesuma , Fred Maurice Ngolè Mboula , Antoine Souloumiac

We consider the problem of Gaussian multiplier bootstrap procedures for the $k$th largest statistics and functions of the top $k$ order statistics, which are commonly encountered in high-dimensional statistical inference. Such a problem has…

统计理论 · 数学 2026-03-04 Yixi Ding , Qizhai Li , Yuke Shi , Liuquan Sun , Luobin Zhang

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
‹ 上一页 1 2 3 10 下一页 ›