Superiority of GNN over NN in generalizing bandlimited functions

06/13/2022
by   A. Martina Neuman, et al.
0

We constructively show, via rigorous mathematical arguments, that GNN architectures outperform those of NN in approximating bandlimited functions on compact d-dimensional Euclidean grids. We show that the former only need ℳ sampled functional values in order to achieve a uniform approximation error of O_d(2^-ℳ^1/d) and that this error rate is optimal, in the sense that, NNs might achieve worse.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset