On the Performance of Clustering in Hilbert Spaces
From MaRDI portal
Publication:3604446
DOI10.1109/TIT.2007.913516zbMath1304.62088MaRDI QIDQ3604446
Gérard Biau, Luc P. Devroye, Gábor Lugosi
Publication date: 24 February 2009
Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1109/tit.2007.913516
clustering; Hilbert space; vector quantization; \(k\)-means; empirical risk minimization; random projections
62H30: Classification and discrimination; cluster analysis (statistical aspects)
68T10: Pattern recognition, speech recognition
60B11: Probability theory on linear topological spaces
94A29: Source coding
Related Items
On the limits of clustering in high dimensions via cost functions, Learning Finite-Dimensional Coding Schemes with Nonlinear Reconstruction Maps, Convergence rate of optimal quantization grids and application to empirical measure, Projection-based curve clustering, Error Analysis of Coefficient-Based Regularized Algorithm for Density-Level Detection, Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes, Also for \(k\)-means: more data does not imply better performance, Fast rates for empirical vector quantization, A partial overview of the theory of statistics with functional data, A statistical view of clustering performance through the theory of \(U\)-processes, Concentration inequalities for non-Lipschitz functions with bounded derivatives of higher order, Dimensionality reduction with subgaussian matrices: a unified theory, Robust Bregman clustering, Empirical risk minimization for heavy-tailed losses, Quantization and clustering with Bregman divergences, A notion of stability for \(k\)-means clustering, On Hölder fields clustering, Wasserstein upper bounds of the total variation for smooth densities, Robust \(k\)-means clustering for distributions with two moments, On strong consistency of kernel \(k\)-means: a Rademacher complexity approach, Biclustering analysis of functionals via penalized fusion, A quantum algorithm of K-means toward practical use, A \(k\)-points-based distance for robust geometric inference, Posterior asymptotics in Wasserstein metrics on the real line, Convergence rates of learning algorithms by random projection, Quantization and clustering on Riemannian manifolds with an application to air traffic analysis, Nonasymptotic bounds for vector quantization in Hilbert spaces, \(L_1\)-quantization and clustering in Banach spaces, Pointwise Convergence of the Lloyd I Algorithm in Higher Dimension, A Vector-Contraction Inequality for Rademacher Complexities, Random projections and Hotelling’s T2 statistics for change detection in high-dimensional data streams, THE COEFFICIENT REGULARIZED REGRESSION WITH RANDOM PROJECTION, Convergence of the $k$-Means Minimization Problem using $\Gamma$-Convergence
