Orthogonally Decoupled Variational Fourier Features
Reviewed by Pithpith:JYDUC77Qopen to challenge →
read the original abstract
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
End-to-end probabilistic hierarchical forecasting of large hierarchies via probabilistic top-down
e2eTD forecasts a small subset of aggregate series (~0.3% of hierarchy) and propagates joint samples via probabilistic top-down disaggregation to produce coherent probabilistic forecasts, achieving lowest weighted sca...
-
Model selection with proper scoring rules on data sets of time series: prefer the mean scaled score
Mean scaled score is recommended over rank-based aggregation for model selection on time series datasets because skewness causes non-mean criteria to select misspecified models with short tests.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.