paper-with-me

홈 › Papers

Clustering a Mixture of Gaussians with Unknown Covariance

2021-10-04 · Damek Davis, Mateo Díaz, Kaizheng Wang

We investigate a clustering problem with data from a mixture of Gaussians that share a common but unknown, and potentially ill-conditioned, covariance matrix. We start by considering Gaussian mixtures with two equally-sized components and derive a Max-Cut integer program based on maximum likelihood estimation. We prove its solutions achieve the optimal misclassification rate when the number of samples grows linearly in the dimension, up to a logarithmic factor. However, solving the Max-cut problem appears to be computationally intractable. To overcome this, we develop an efficient spectral algorithm that attains the optimal rate but requires a quadratic sample size. Although this sample complexity is worse than that of the Max-cut problem, we conjecture that no polynomial-time method can perform better. Furthermore, we gather numerical and theoretical evidence that supports the existence of a statistical-computational gap. Finally, we generalize the Max-Cut program to a $k$-means program that handles multi-component mixtures with possibly unequal weights. It enjoys similar optimality guarantees for mixtures of distributions that satisfy a transportation-cost inequality, encompassing Gaussian and strongly log-concave distributions.

📄 PDF Abstract BibTeX arXiv:2110.01602

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Similar Papers 제목 키워드 기반

Robustly Clustering a Mixture of Gaussians

2019-11-26 · He Jia, Santosh Vempala

We give an efficient algorithm for robustly clustering of a mixture of two arbitrary Gaussians, a central open problem in the theory of computationally efficient robust estimation, assuming only that the the means of the…

ClusteringPosition

Dimension Reduction via Sum-of-Squares and Improved Clustering Algorithms for Non-Spherical Mixtures

2024-11-19 · Prashanti Anderson, Mitali Bafna, Rares-Darius Buhai, Pravesh K. Kothari 외

We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine, based on the sum-of-squares method, that finds a low-dimensional separation-preserv…

ClusteringDimensionality Reduction

Ten Steps of EM Suffice for Mixtures of Two Gaussians

2016-09-01 · Constantinos Daskalakis, Christos Tzamos, Manolis Zampetakis

The Expectation-Maximization (EM) algorithm is a widely used method for maximum likelihood estimation in models with latent variables. For estimating mixtures of Gaussians, its iteration can be viewed as a soft version o…

ClusteringVocal Bursts Valence Prediction

Optimal Clustering in Anisotropic Gaussian Mixture Models

2021-01-14 · Xin Chen, Anderson Y. Zhang

We study the clustering task under anisotropic Gaussian Mixture Models where the covariance matrices from different clusters are unknown and are not necessarily the identical matrix. We characterize the dependence of sig…

Clustering

Clustering Mixtures of Bounded Covariance Distributions Under Optimal Separation

2023-12-19 · Ilias Diakonikolas, Daniel M. Kane, Jasper C. H. Lee, Thanasis Pittas

We study the clustering problem for mixtures of bounded covariance distributions, under a fine-grained separation assumption. Specifically, given samples from a $k$-component mixture distribution $D = \sum_{i =1}^k w_i P…

Clustering