Ask a Question

Prefer a chat interface with context about you and your work?

Compressible Spectral Mixture Kernels with Sparse Dependency Structures for Gaussian Processes

Compressible Spectral Mixture Kernels with Sparse Dependency Structures for Gaussian Processes

Spectral mixture kernels comprise a powerful class of optimal kernels for Gaussian processes (GPs) to describe complex patterns. This paper introduces model compression and time- and phase (TP) modulated dependency structures to the original spectral mixture (SM) kernel for improved GP model expressiveness. Specifically, by adopting Bienaym´es identity, we generalize …