The uniqueness of a good optimum for K-means

Authors:
Marina Meilă
Affiliations:
University of Washington, Seattle, WA
Venue:
ICML '06 Proceedings of the 23rd international conference on Machine learning
Year:
2006

Citing 6
Cited 11

Combinatorial optimization: algorithms and complexity

Combinatorial optimization: algorithms and complexity
Learning Mixtures of Gaussians

FOCS '99 Proceedings of the 40th Annual Symposium on Foundations of Computer Science
Stability-based validation of clustering solutions

Neural Computation
K-means clustering via principal component analysis

ICML '04 Proceedings of the twenty-first international conference on Machine learning
A spectral algorithm for learning mixture models

Journal of Computer and System Sciences - Special issue on FOCS 2002
Comparing clusterings: an axiomatic view

ICML '05 Proceedings of the 22nd international conference on Machine learning

A dependence maximization view of clustering

Proceedings of the 24th international conference on Machine learning
Approximate clustering without the approximation

SODA '09 Proceedings of the twentieth Annual ACM-SIAM Symposium on Discrete Algorithms
Toward autonomic grids: analyzing the job flow with affinity streaming

Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining
Distributed and Incremental Clustering Based on Weighted Affinity Propagation

Proceedings of the 2008 conference on STAIRS 2008: Proceedings of the Fourth Starting AI Researchers' Symposium
Data clustering: 50 years beyond K-means

Pattern Recognition Letters
Spectral clustering with more than K eigenvectors

Neurocomputing
Center-based clustering under perturbation stability

Information Processing Letters
Clustering under approximation stability

Journal of the ACM (JACM)
Random walk distances in data clustering and applications

Advances in Data Analysis and Classification
Clustering genome data based on approximate matching

International Journal of Data Analysis Techniques and Strategies
Variational learning of a Dirichlet process of generalized Dirichlet distributions for simultaneous clustering and feature selection

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

If we have found a "good" clustering C of a data set, can we prove that C is not far from the (unknown) best clustering Copt of these data? Perhaps surprisingly, the answer to this question is sometimes yes. When "goodness" is measured by the distortion of K-means clustering, this paper proves spectral bounds on the distance d(C, Copt). The bounds exist in the case when the data admits a low distortion clustering.