Configuration-Dependent Lower Bounds for Approximation by Shallow ReLU^k Networks on the Sphere

arXiv:2510.04060v3 Announce Type: replace-cross Abstract: We establish two related but logically distinct results for shallow ReLU^k neural networks on the unit sphere SS^d. First, for an arbitrary set of inner neural-network parameters, the best L^2(SS^d) approximation of a fixed target function with smoothness r>frac{d+2k+1}{2} admits an asymptotic lower bound given by a constant multiple of n^{-1/2}nderline{h}^{k+1/2}, where nderline{h} denotes the antipodal separation distance of the normalized inner-parameter set. This lower bound depends explicitly on the parameter configuration through nderline{h} and applies without additional assumptions on the parameters. Second, for antipodally quasi-uniform parameters, nderline{h}simeq n^{-1/d}, and the lower bound establishes the exact saturation order n^{-frac{d+2k+1}{2d}} for such parameter families: a target function with regularity greater than frac{d+2k+1}{2} and satisfying the required parity condition can be approximated at this rate, whereas approximation at any strictly faster rate forces the target function to be zero. Our results therefore place linearized neural-network approximation within the classical saturation framework and show that, although ReLU^k network spaces can outperform finite elements of the same degree, this advantage is intrinsically limited.

Related

• Nonlinear Dynamics In Optimization Landscape of Shallow Neural Networks with Tunable Leaky ReLU
• Shallow ReLU^s Networks in L^p-Type and Sobolev Spaces: Approximation and Path-Norm Controlled Generalization

Source: arXiv cs.LG | 2026-09-11