A Gaussian-kernel diffusion operator on feature clouds yields closed-form class affinities and spectra in Gaussian models, with provably smooth observables under perturbations.
Laplacian eigenmaps for dimensionality reduction and data representation.Neural Computation, 15(6):1373–1396
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces finite-lag operator geometry deriving a source-centered transport tensor that decomposes into spread and coherent displacement plus an antisymmetric circulation measure, with proofs of covariance and stability.
citing papers explorer
-
Diffusion Operator Geometry of Feedforward Representations
A Gaussian-kernel diffusion operator on feature clouds yields closed-form class affinities and spectra in Gaussian models, with provably smooth observables under perturbations.
-
Finite-Lag Operator Geometry of Recurrent Representations
Introduces finite-lag operator geometry deriving a source-centered transport tensor that decomposes into spread and coherent displacement plus an antisymmetric circulation measure, with proofs of covariance and stability.