Asymptotic convexity of wide and shallow neural networks
Vivek Borkar, Parthe Pandit
Published: 2025/6/23
Abstract
For a simple model of shallow and wide neural networks, we show that the epigraph of its input-output map as a function of the network parameters approximates epigraph of a. convex function in a precise sense. This leads to a plausible explanation of their observed good performance.