Manifold learning with bi-stochastic kernels
This provides theoretical insights for manifold learning, but it is incremental as it builds on existing kernel normalization methods.
The paper determines the infinitesimal generator of a diffusion process defined by a bi-stochastic kernel on a Riemannian manifold, showing how it depends on nonuniform data sampling and specified measures, with a special case linking to the heat kernel.
In this paper we answer the following question: what is the infinitesimal generator of the diffusion process defined by a kernel that is normalized such that it is bi-stochastic with respect to a specified measure? More precisely, under the assumption that data is sampled from a Riemannian manifold we determine how the resulting infinitesimal generator depends on the potentially nonuniform distribution of the sample points, and the specified measure for the bi-stochastic normalization. In a special case, we demonstrate a connection to the heat kernel. We consider both the case where only a single data set is given, and the case where a data set and a reference set are given. The spectral theory of the constructed operators is studied, and Nyström extension formulas for the gradients of the eigenfunctions are computed. Applications to discrete point sets and manifold learning are discussed.