Consistency of spectral clustering
| dc.creator | von Luxburg, Ulrike | |
| dc.creator | Belkin, Mikhail | |
| dc.creator | Bousquet, Olivier | |
| dc.date | 2008-04-04 | |
| dc.date.accessioned | 2026-07-07T12:18:06Z | |
| dc.date.available | 2026-07-07T12:18:06Z | |
| dc.description | Consistency is a key property of all statistical procedures analyzing randomly sampled data. Surprisingly, despite decades of work, little is known about consistency of most clustering algorithms. In this paper we investigate consistency of the popular family of spectral clustering algorithms, which clusters the data with the help of eigenvectors of graph Laplacian matrices. We develop new methods to establish that, for increasing sample size, those eigenvectors converge to the eigenvectors of certain limit operators. As a result, we can prove that one of the two major classes of spectral clustering (normalized clustering) converges under very general conditions, while the other (unnormalized clustering) is only consistent under strong additional assumptions, which are not always satisfied in real data. We conclude that our analysis provides strong evidence for the superiority of normalized spectral clustering. | |
| dc.description | Published in at http://dx.doi.org/10.1214/009053607000000640 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org) | |
| dc.identifier | https://arxiv.org/abs/0804.0678 | |
| dc.identifier | http://arxiv.org/abs/0804.0678 | |
| dc.identifier | Annals of Statistics 2008, Vol. 36, No. 2, 555-586 | |
| dc.identifier | doi:10.1214/009053607000000640 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/212294 | |
| dc.subject | Statistics Theory | |
| dc.subject | 62G20 (Primary) 05C50 (Secondary) | |
| dc.title | Consistency of spectral clustering | |
| dc.type | text |