A sampling-based RKHS norm estimator grounded in recent superconvergence theory for kernel methods, applicable to broad function classes with modest prior knowledge.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A stable operating interval for the Gaussian scale parameter ε in KANs is ε ∈ [1/(G-1), 2/(G-1)], derived from first-layer feature geometry and validated across multiple approximation and physics-informed problems.
citing papers explorer
-
Reliable sampling-based RKHS norm estimation via superconvergence
A sampling-based RKHS norm estimator grounded in recent superconvergence theory for kernel methods, applicable to broad function classes with modest prior knowledge.
-
Scale-Parameter Selection in Gaussian Kolmogorov-Arnold Networks
A stable operating interval for the Gaussian scale parameter ε in KANs is ε ∈ [1/(G-1), 2/(G-1)], derived from first-layer feature geometry and validated across multiple approximation and physics-informed problems.