Neural Processes (NPs; Garnelo et al., 2018a,b) are a rich class of models for meta-learning that map data sets directly to predictive stochastic processes. We provide a rigorous analysis of the standard maximum-likelihood objective used to train conditional NPs. Moreover, we propose a new member to the Neural Process family called the Gaussian Neural Process (GNP), which models predictive correlations, incorporates translation equivariance, provides universal approximation guarantees, and demonstrates encouraging performance.
@article{arxiv.2101.03606,
title = {The Gaussian Neural Process},
author = {Wessel P. Bruinsma and James Requeima and Andrew Y. K. Foong and Jonathan Gordon and Richard E. Turner},
journal= {arXiv preprint arXiv:2101.03606},
year = {2021}
}
Comments
34 pages; includes supplementary material; to appear in AABI 2020