Spectral Barron space and deep neural network approximation
share
We prove the sharp embedding between the spectral Barron space and the Besov space. Given the spectral Barron space as the target function space, we prove a dimension-free result that if the neural network contains L hidden layers with N units per layer, then the upper and lower bounds of the L^2-approximation error are 𝒪(N^-sL) with 0 < sL≤ 1/2, where s is the smoothness index of the spectral Barron space.
READ FULL TEXT
