AI RESEARCH
Variational Kolmogorov-Arnold Network
arXiv CS.LG
•
ArXi:2507.02466v2 Announce Type: replace Kolmogoro-Arnold Networks (KANs) offer a theoretically grounded alternative to multi-layer perceptrons by representing multivariate functions as compositions of univariate basis functions. However, a critical limitation of KANs is the need to manually specify the number of basis functions per layer -- a hyperparameter that directly controls model capacity and substantially impacts performance, yet whose optimal value varies unpredictably across tasks.