The Gaussian Neural Process
This work provides an incremental improvement to the Neural Process family for researchers working on meta-learning and stochastic processes.
This paper analyzes the training objective of conditional Neural Processes and introduces the Gaussian Neural Process (GNP). The GNP models predictive correlations, incorporates translation equivariance, and offers universal approximation guarantees.
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.