Show simple item record

dc.contributor.authorAli, Hafiz Tiomoko
dc.contributor.authorKammoun, Abla
dc.contributor.authorCouillet, Romain
dc.date.accessioned2019-03-14T14:14:37Z
dc.date.available2019-03-14T14:14:37Z
dc.date.issued2018-09-21
dc.identifier.citationAli HT, Kammoun A, Couillet R (2018) Random Matrix Asymptotics of Inner Product Kernel Spectral Clustering. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Available: http://dx.doi.org/10.1109/ICASSP.2018.8462052.
dc.identifier.doi10.1109/ICASSP.2018.8462052
dc.identifier.urihttp://hdl.handle.net/10754/631603
dc.description.abstractWe 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.
dc.description.sponsorshipThe work of R. Couillet and H. Tiomoko Ali is supported by the ANR Project RMT4GRAPH (ANR-14-CE28-0006)
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/8462052
dc.subjectInner product kernels
dc.subjectRandom matrices
dc.subjectRandom matrix theory
dc.subjectSpectral clustering
dc.titleRandom Matrix Asymptotics of Inner Product Kernel Spectral Clustering
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journal2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
dc.conference.date2018-04-15 to 2018-04-20
dc.conference.name2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
dc.conference.locationCalgary, AB, CAN
dc.contributor.institutionCentralexupelec, Université Paris-Saclay, Gif-sur- Yvette, , France
kaust.personKammoun, Abla
dc.date.published-online2018-09-21
dc.date.published-print2018-04


This item appears in the following Collection(s)

Show simple item record