Geometric Learning with Positively Decomposable Kernels

Abstract

Kernel methods are powerful tools in machine learning. Classical kernel methods are based on positive-definite kernels, which map data spaces into reproducing kernel Hilbert spaces (RKHS). For non-Euclidean data spaces, positive-definite kernels are difficult to come by. In this case, we propose the use of reproducing kernel Krein space (RKKS) based methods, which require only kernels that admit a positive decomposition. We show that one does not need to access this decomposition in order to learn in RKKS. We then investigate the conditions under which a kernel is positively decomposable. We show that invariant kernels admit a positive decomposition on homogeneous spaces under tractable regularity assumptions. This makes them much easier to construct than positive-definite kernels, providing a route for learning with kernels for non-Euclidean data. By the same token, this provides theoretical foundations for RKKS-based methods in general.

References in corpus (4)

• Riemannian statistics meets random matrix theory: towards learning from high-dimensional covariance matrices
• Gaussian kernels on non-simply-connected closed Riemannian manifolds are never positive definite
• Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces
• Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case