Learning manifold diffusion semigroups from graph transition matrices

We consider graph diffusion processes constructed from finite i.i.d. samples drawn from an unknown manifold embedded in ambient Euclidean space, where the graph affinity is defined by an ambient Gaussian kernel matrix. We show that the manifold heat semigroup Qt = etDelta can be approximated directly by iterating the graph transition matrix P, under only low regularity assumptions on the test function f, including the case f ∈ L^∞. We bound | Pn f - Qt f | in ∞-norm, with the operator application to f properly defined, and we recover the classical graph-Laplacian pointwise rate O(N-2/(d+6)) up to logarithmic factors, for diffusion times t up to O(1) and longer. The rate holds for in-sample error as well as out-of-sample generalization, where the estimator of Qt f at a new point is defined via kernel convolution. To handle non-uniform sampling densities on the manifold, we introduce a right-normalization of the graph transition matrix; under the assumption that the sampling density p is C3 and bounded away from zero, the same convergence rates hold. We numerically demonstrate the performance of the proposed estimator on simulated data.