math.NAcs.LGmath.FAmath.MG

Spectral Landmarks: Alignment of Landmark Kernel Translates with the Leading Eigenfunctions of a Kernel Operator

📅 👥 1 authors arXiv:2611.20336v1

Authors

Abstract

We study the problem of choosing $m$ landmark points so that the span of the kernel translates is as close as possible to the leading $s$-dimensional eigenspace of a positive-definite kernel. The natural measure is the Hilbert-Schmidt operator discrepancy between the reproducing-kernel-Hilbert-space (RKHS) projectors onto the two subspaces. We give a closed form spectral alignment function in terms of the truncated Mercer kernel and relate it to the classical integrated power function (Nyström trace error) through a two-sided sandwich bound. Minimizing the function by gradient descent on the landmark coordinates produces landmark sets that are evenly spaced. Theoretical results show that optimal configurations are those whose eigenfunction sampling matrix is a scaled isometry. On homogeneous spaces these are exactly the minimal equal-weight cubature rules for products of leading eigenfunctions, and for every $m\ge s$ they are the configurations whose sampled eigenfunctions form a unit-norm tight frame. Experiments on $\mathbb{S}^1$ and $\mathbb{S}^2$ agree with the theory. On the circle, with $s\le2m$ and a moderate bandwidth, every random start converges to equispaced landmarks, and on the sphere the optimizer recovers the regular tetrahedron, octahedron, and icosahedron from random starts. Finally, we analyze the numerical conditioning of the problem.

Paper Information

arXiv ID:
2611.20336v1
Published:

Related Categories

math.NAcs.LGmath.FAmath.MG