# LTBs-KAN: Linear-Time B-splines Kolmogorov-Arnold Networks Source: [LTBs-KAN: Linear-Time B-splines Kolmogorov-Arnold Networks]() Collection index: [llms.txt]() Data updated: 2026-04-28T05:00:04.744Z Authors: Eduardo Said Merin-Martinez, Andres Mendez-Vazquez, Eduardo Rodriguez-Tello Published: 2026-04-23T19:47:13.000Z ## Abstract Kolmogorov-Arnold Networks (KANs) are a recent neural network architecture offering an alternative to Multilayer Perceptrons (MLPs) with improved explainability and expressibility. However, KANs are significantly slower than MLPs due to the recursive nature of B-spline function computations, limiting their application. This work addresses these issues by proposing a novel base-spline Linear-Time B-splines Kolmogorov-Arnold Network (LTBs-KAN) with linear complexity. Unlike previous methods that rely on the Boor-Mansfield-Cox spline algorithm or other computationally intensive mathematical functions, our approach significantly reduces the computational burden. Additionally, we further reduce model's parameter through product-of-sums matrix factorization in the forward pass without sacrificing performance. Experiments on MNIST, Fashion-MNIST and CIFAR-10 demonstrate that LTBs-KAN achieves good time complexity and parameter reduction, when used as building architectural blocks, compared to other KAN implementations. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on Fashion-MNIST (Accuracy, Precision, Recall, F1)](): Image Classification; Fashion MNIST; Accuracy: 87.44. - [Image Classification on MNIST (test) (Standard Classification Report)](): Image Classification; MNIST (test); Accuracy: 96.32. ## Original sources and implementation [Original paper]() [PDF]()