REVIEW 2 cited by
Spectral Convergence Rate of Graph Laplacian
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
Laplacian Eigenvectors of the graph constructed from a data set are used in many spectral manifold learning algorithms such as diffusion maps and spectral clustering. Given a graph constructed from a random sample of a $d$-dimensional compact submanifold $M$ in $\mathbb{R}^D$, we establish the spectral convergence rate of the graph Laplacian. It implies the consistency of the spectral clustering algorithm via a standard perturbation argument. A simple numerical study indicates the necessity of a denoising step before applying spectral algorithms.
Forward citations
Cited by 2 Pith papers
-
How well behaved is finite dimensional Diffusion Maps?
Finite-dimensional Diffusion Maps on submanifolds preserve almost uniform density, polynomial approximation, and reach, with embedding error O((log n/n)^{1/(8d+16)}) and tangent space error bounded by C (log n/n)^{(k-...
-
Analysis of Semi-Supervised Learning on Hypergraphs
For random geometric hypergraphs, the standard variational semi-supervised learning problem converges in the large-data limit to a density-weighted p-Laplacian problem, making it a first-order graph method; the propos...
Discussion (0). Continue with ORCID to comment.