Orthogonally Decoupled Variational Fourier Features

07/13/2020
by   Dario Azzimonti, et al.
0

Sparse inducing points have long been a standard method to fit Gaussian processes to big data. In the last few years, spectral methods that exploit approximations of the covariance kernel have shown to be competitive. In this work we exploit a recently introduced orthogonally decoupled variational basis to combine spectral methods and sparse inducing points methods. We show that the method is competitive with the state-of-the-art on synthetic and on real-world data.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset