AI RESEARCH
Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks
arXiv CS.LG
•
ArXi:2604.03345v1 Announce Type: new Kolmogoro-Arnold Networks (KANs) have recently emerged as a powerful architecture for various machine learning applications. However, their unique structure raises significant concerns regarding their computational overhead. Existing studies primarily evaluate KAN complexity in terms of Floating-Point Operations (FLOPs) required for GPU-based