Abstract
In this paper we introduce a novel neural network architecture, in which weight matrices are reparametrized in terms of low-dimensional vectors, interacting through kernel functions. A layer of our network can be interpreted as introducing a (potentially infinitely wide) linear layer be tween input and output. We describe the theory underpinning this model and validate it with concrete examples, exploring how it can be used to impose structure on neural networks in diverse applications ranging from data visualization to recommender systems. We achieve state-of-theart performance in a collaborative filtering task (MovieLens).