Multi-kernel spectral clustering: Entrywise eigenvector perturbation bounds and exact recovery
Zeqin Lin, Guangming Pan, Zhixiang Zhang, Yinbing Zhou
stat.ML, cs.LG, math.ST, stat.TH
Submitted: 2026-08-09
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Universality for the global spectrum of random inner-product kernel matrices in the polynomial regime
- Anisotropic local law for non-separable sample covariance matrices
- Extremal Eigenvalues of Random Kernel Matrices with Polynomial Scaling
- Unified $\ell_{2\rightarrow\infty}$ Eigenspace Perturbation Theory for Symmetric Random Matrices
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches