On clusterings: Good, bad and spectral

We motivate and develop a natural bicriteria measure for assessing the quality of a clustering that avoids the drawbacks of existing measures. A simple recursive heuristic is shown to have poly-logarithmic worst-case guarantees under the new measure. The main result of the article is the analysis of a popular spectral algorithm. One variant of spectral clustering turns out to have effective worst-case guarantees; another finds a "good" clustering, if one exists.

[1]  David R. Karger,et al.  Approximating s – t Minimum Cuts in ~ O(n 2 ) Time , 2007 .

[2]  Anna R. Karlin,et al.  Spectral analysis of data , 2001, STOC '01.

[3]  Charles J. Alpert,et al.  Spectral Partitioning: The More Eigenvectors, The Better , 1995, 32nd Design Automation Conference.

[4]  Mark Jerrum,et al.  Approximate Counting, Uniform Generation and Rapidly Mixing Markov Chains , 1987, International Workshop on Graph-Theoretic Concepts in Computer Science.

[5]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Frank Thomson Leighton,et al.  Multicommodity max-flow min-cut theorems and their use in designing approximation algorithms , 1999, JACM.

[7]  Shang-Hua Teng,et al.  Spectral partitioning works: planar graphs and finite element meshes , 1996, Proceedings of 37th Conference on Foundations of Computer Science.

[8]  Yair Weiss,et al.  Segmentation using eigenvectors: a unifying view , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  David B. Shmoys,et al.  A constant-factor approximation for the k-median problem , 1999 .

[10]  Rajeev Motwani,et al.  Incremental Clustering and Dynamic Information Retrieval , 2004, SIAM J. Comput..

[11]  Santosh S. Vempala,et al.  On clusterings-good, bad and spectral , 2000, Proceedings 41st Annual Symposium on Foundations of Computer Science.

[12]  Santosh S. Vempala,et al.  Latent Semantic Indexing , 2000, PODS 2000.

[13]  Andrew B. Kahng,et al.  Spectral Partitioning with Multiple Eigenvectors , 1999, Discret. Appl. Math..

[14]  Alan M. Frieze,et al.  Clustering in large graphs and matrices , 1999, SODA '99.

[15]  Frank Thomson Leighton,et al.  An approximate max-flow min-cut theorem for uniform multicommodity flow problems with applications to approximation algorithms , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

[16]  G. Stewart.  Error and Perturbation Bounds for Subspaces Associated with Certain Eigenvalue Problems , 1973 .

[17]  Alan M. Frieze,et al.  Fast Monte-Carlo algorithms for finding low-rank approximations , 1998, Proceedings 39th Annual Symposium on Foundations of Computer Science (Cat. No.98CB36280).

[18]  Vijay V. Vazirani,et al.  Approximation algorithms for metric facility location and k-Median problems using the primal-dual schema and Lagrangian relaxation , 2001, JACM.

[19]  Santosh S. Vempala,et al.  Latent semantic indexing: a probabilistic analysis , 1998, PODS '98.

[20]  A. Frieze,et al.  A simple heuristic for the p-centre problem , 1985 .

[21]  Inderjit S. Dhillon,et al.  Co-clustering documents and words using bipartite spectral graph partitioning , 2001, KDD '01.

[22]  Vijay V. Vazirani,et al.  Primal-dual approximation algorithms for metric facility location and k-median problems , 1999, 40th Annual Symposium on Foundations of Computer Science (Cat. No.99CB37039).

[23]  V VaziraniVijay,et al.  Approximation algorithms for metric facility location and k-Median problems using the primal-dual schema and Lagrangian relaxation , 2001 .

[24]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[25]  Piotr Indyk.  A sublinear time approximation scheme for clustering in metric spaces , 1999, 40th Annual Symposium on Foundations of Computer Science (Cat. No.99CB37039).

[26]  Sudipto Guha,et al.  A constant-factor approximation algorithm for the k-median problem (extended abstract) , 1999, STOC '99.