On the minimum of the mean-squared error in 2-means clustering

DOI10.2140/involve.2019.12.301zbMath1406.62067arXiv1710.09693OpenAlexW2767194928WikidataQ129092160 ScholiaQ129092160MaRDI QIDQ1624878

Bernhard G. Bodmann, Craig J. George

Publication date: 16 November 2018

Published in: Involve (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1710.09693

zbMATH Keywords

performance guaranteesmean-squared error\(k\)-means clustering

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Nonparametric estimation (62G05)

Related Items

The Ratio-Cut Polytope and K-Means Clustering

Cites Work

• \(k\)-means requires exponentially many iterations even in the plane
• A central limit theorem for k-means clustering
• Probably certifiably correct \(k\)-means clustering
• Hypercontractivity for the heat semigroup for ultraspherical polynomials and on the n-sphere
• Foundations of quantization for probability distributions
• Exponential rate of convergence for Lloyd's method I
• K-Means-Type Algorithms: A Generalized Convergence Theorem and Characterization of Local Optimality
• Multidimensional asymptotic quantization theory with<tex>r</tex>th power distortion measures
• Centroidal Voronoi Tessellations: Applications and Algorithms
• Least squares quantization in PCM
• Approximating K‐means‐type Clustering via Semidefinite Programming