neural-processes

This paper theoretically characterizes the representational capacity of Neural Process (NP) architectures, proving a strict hierarchy among Conditional, Attentive, Convolutional, and Transformer NPs, and showing that finite-dimensional latent variables do not expand representational capacity beyond the encoder.

This paper decomposes the predictive KL divergence between Gaussian process and latent neural process posteriors into three terms, providing upper bounds that characterize approximation errors and connecting representation dimension to kernel smoothness.