The Gaussian Neural Process

Wessel Bruinsma, James Requeima, Andrew Y. K. Foong, Jonathan Gordon, Richard E Turner

Keywords: Meta-Learning, Neural Processes, Gaussian Processes

Abstract: 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.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2101.03606/code)