arXiv stat.ML
· Papers
Multi-kernel spectral clustering: Entrywise eigenvector perturbation bounds and exact recovery
arXiv:2608.08704v1 Announce Type: new Abstract: Kernel spectral clustering with a single bandwidth can be inadequate for data exhibiting multiple characteristic pairwise-distance scales, a problem particularly prevalent in the high-dimensional regime. We address this issue through a multi-kernel formulation that aggreg