Abstract | ||
---|---|---|
We introduce Latent Gaussian Process Regression which is a latent variable extension allowing modelling of non-stationary processes using stationary GP priors. The approach is built on extending the input space of a regression problem with a latent variable that is used to modulate the covariance function over the input space. We show how our approach can be used to model non-stationary processes but also how multi-modal or non-functional processes can be described where the input signal cannot fully disambiguate the output. We exemplify the approach on a set of synthetic data and provide results on real data from geostatistics. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Machine Learning | Kriging,Data mining,Covariance function,Latent variable model,Latent class model,Latent variable,Synthetic data,Gaussian process,Artificial intelligence,Logistic regression,Mathematics,Machine learning |
DocType | Volume | Citations |
Journal | abs/1707.05534 | 2 |
PageRank | References | Authors |
0.39 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Erik Bodin | 1 | 3 | 1.75 |
Neill D. F. Campbell | 2 | 303 | 18.10 |
carl henrik ek | 3 | 327 | 30.76 |