Posterior Contraction Rates for Sparse Kolmogorov-Arnold Networks in Anisotropic Besov Spaces

ArXi:2605.11652v1 Announce Type: cross We study posterior contraction rates for sparse Bayesian Kolmogoro-Arnold networks (KANs) over anisotropic Beso spaces, providing a statistical foundation of KANs from a Bayesian point of view. We show that sparse Bayesian KANs equipped with spike-and-slab-type sparsity priors attain the near-minimax posterior contraction. In particular, the contraction rate depends on the intrinsic anisotropic smoothness of the underlying function.