SupplementaryMaterial: Meta-LearningStationaryStochasticProcess PredictionwithConvolutionalNeuralProcesses

In this setting, we implementφ, by selecting the context points, and prepend the context mask: φ = [Mc,Zc]>. C.2 Pseudo-CodefortheConvNP The ConvNP can be implemented very simply by passing samples from the ConvCNP through an additional CNN decoder, which we denotedθ.