Deep KANs achieve universal approximation if and only if they include at least one non-affine edge function σ, while two-layer KANs require σ to be nonpolynomial.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks
Deep KANs achieve universal approximation if and only if they include at least one non-affine edge function σ, while two-layer KANs require σ to be nonpolynomial.