Parameter Bounds and Inverse Approximation for Linearized ReLU k Networks on the Sphere

arXiv:2611.00656 · math.NA, cs.NA · Submitted 2026-10-31 · Read on arXiv

math.NA, cs.NA

Submitted: 2026-10-31

Updated: 2026-10-31

License: http://creativecommons.org/licenses/by/4.0/

The gist: We study direct and inverse approximation for linearized shallow ReLU k networks on S d with quasi-uniform hidden parameters.

Abstract

We study direct and inverse approximation for linearized shallow ReLU k networks on S d with quasi-uniform hidden parameters. For 0<α< d+2k+1 over 2d, under the coefficient growth condition (n sum from j=1 to na j,n 2) 1 over 2 at most n αM, we prove that approximation at the order n-d+2k+1 over 2d+α is equivalent to membership in the parity-compatible Besov space B 2, infinity,* d+2k+1 over 2-αd(S d). Mere convergence under the same coefficient budget does not imply this regularity. For unconstrained approximation along a nested parameter sequence, a single ridge function gives a counterexample when α< 1 over 2, whereas for α> 1 over 2 the endpoint Besov inverse conclusion follows from a Bernstein inequality under antipodal quasi-uniformity. The inverse conclusion is also recovered when the prescribed rate holds for two quasi-uniform parameter sequences whose union is antipodally separated.

Sources

Related papers