Shallow neural network approximation in mixed Sobolev spaces

Abstract: We investigate the best $L_2$ approximation of mixed Sobolev spaces by shallow neural networks with $n$ neurons and general activation functions. We first establish an activation-independent Fourier-block principle: if an activation has univariate approximation order $ρ$ in the sense of the Fourier-block property, then the global approximation rate has algebraic order $\min{α,ρ}$ for target functions of mixed smoothness $α$, up to explicit logarithmic factors. To verify this property for concrete activations, we introduce a structured univariate approximation condition that implies the Fourier-block property with explicit parameters. For $\mathrm{ReLU}<sup>k$, a matching algebraic lower bound identifies $\min{α,k+1}$ as the optimal algebraic approximation exponent in any dimension, up to logarithmic factors in the upper bound. The framework also yields the exponent $\min{α,k+1}$ for cardinal B-splines and soft-$\mathrm{ReLU}<sup>k$, and the full mixed-smoothness exponent $α$ for ELU and cosine activations, again up to logarithmic~factors.