Neural Networks, Ridge Splines, and TV Regularization in the Radon Domain

We develop a variational framework to understand the properties of the functions learned by neural networks fit to data. We propose and study of a family of continuous-domain linear inverse problems with total variation-like regularization in the Radon domain subject to data fitting constraints. We derive a representer theorem showing that finite-width, single-hidden layer neural networks are solutions to these inverse problems. We draw on many techniques from variational spline theory and so we propose the notion of a ridge spline, which corresponds to fitting data with a single-hidden layer neural network. The representer theorem is reminiscent of the classical Reproducing Kernel Hilbert space representer theorem, but the neural network problem is set in a non-Hilbertian Banach space. Although the learning problems are posed in the continuous-domain, similar to kernel methods, the problems can be recast as finite-dimensional neural network training problems. These neural network training problems have regularizers which are related to the well-known weight decay and path-norm regularizers. Thus, our result gives insight into functional characteristics of trained neural networks and also into the design neural network regularizers. We also show that these regularizers promote neural network solutions with desirable generalization properties.