Fixed-architecture networks of width O(D) and depth O(r) approximate Hölder functions with parameter magnitude log P = O(ε^{-2D/(r+γ)} log(1/ε)) via CRT encoding.
Illinois Journal of Mathematics , volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
On Explicit Super-Expressive Approximation for Neural Networks
Fixed-architecture networks of width O(D) and depth O(r) approximate Hölder functions with parameter magnitude log P = O(ε^{-2D/(r+γ)} log(1/ε)) via CRT encoding.