Random matrix asymptotics of inner product kernel spectral clustering

Abstract : We study in this article the asymptotic performance of spectral clustering with inner product kernel for Gaussian mixture models of high dimension with numerous samples. As is now classical in large dimensional spectral analysis, we establish a phase transition phenomenon by which a minimum distance between the class means and covariances is required for clustering to be possible from the dominant eigenvectors. Beyond this phase transition, we evaluate the asymptotic content of the dominant eigenvectors thus allowing for a full characterization of clustering performance. However, a surprising finding is that in some particular scenarios, the phase transition does not occur and clustering can be achieved irrespective of the class means and covariances. This is evidenced here in the case of the mixture of two Gaussian datasets having the same means and arbitrary difference between covariances.
Liste complète des métadonnées

Cited literature [9 references]  Display  Hide  Download

Contributor : Hafiz Tiomoko Ali <>
Submitted on : Monday, June 11, 2018 - 10:21:15 AM
Last modification on : Friday, April 12, 2019 - 1:06:57 PM
Document(s) archivé(s) le : Wednesday, September 12, 2018 - 9:23:16 PM


Files produced by the author(s)



Hafiz Tiomoko Ali, Abla Kammoun, Romain Couillet. Random matrix asymptotics of inner product kernel spectral clustering. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2018), Apr 2018, Calgary, Canada. ⟨10.1109/icassp.2018.8462052 ⟩. ⟨hal-01812005⟩



Record views


Files downloads