KANs

2 items

RESEARCHarXiv CS.LG·26d ago

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise

This research establishes the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained with mini-batch SGD, including differentially private SGD (DP-SGD) with correlated noise. It covers more practical scenarios than prior KAN theory and provides sharper results for fixed-second-layer specializations.

neural networks Optimization Differential Privacy machine learning

RESEARCHarXiv CS.LG·4/27/2026

LTBs-KAN: Linear-Time B-splines Kolmogorov-Arnold Networks

LTBs-KAN is a novel neural network architecture designed to overcome the computational slowness of traditional KANs by offering linear complexity and reduced parameters. Experiments demonstrate significant improvements in computational efficiency and parameter reduction on common datasets like MNIST, Fashion-MNIST, and CIFAR-10.

neural networks B-splines deep learning Computational Efficiency