aiqbench analysis
This paper addresses a critical bottleneck in Kolmogorov-Arnold Networks (KANs) by introducing concurrency-driven strategies to overcome the sequential nature of their Newton-Kaczmarz training algorithm. The authors propose three specific optimizations, including disjoint dataset partitioning and an FPGA-specific division-free implementation, which collectively enable substantial parallel acceleration compared to classical multilayer perceptrons. These results provide a concrete pathway for scaling KANs in high-performance computing environments where hardware efficiency is paramount.
Concurrent training methods for Kolmogorov-Arnold networks: Disjoint datasets and FPGA implementation
arXiv:2512.18921v5 Announce Type: replace Abstract: The present paper introduces concurrency-driven enhancements to the training algorithm for the Kolmogorov-Arnold networks (KANs) that is based on the Newton-Kaczmarz (NK) method. Prior research shows that KANs trained using the NK-based approach outperform classical neural networks (multilayer perceptrons - MLPs) both in terms of accuracy and training time. Up to now, the fundamental limitation of the algorithm has been the sequential computation of the updates - each update depends on the results of the previous step, obstructing parallelisation; even though parallelisation of some parts of the algorithm, such as the evaluation of the basis functions, has already been proposed and tested. However, substantial acceleration is achievable. Three complementary concurrency-driven novel strategies are proposed in the present paper: (i) a pre-training procedure tailored to the NK updates' structure, (ii) training on disjoint subsets of data together with models' merging, and (iii) a division-free customisation of the algorithm for field-programmable gate arrays (FPGAs), which is implemented and tested directly on the device. Computational experiments are used to assess the scalability and to compare the authors' KAN implementation with popular MLP packages. All presented experimental results are fully reproducible, with the complete source codes available online.
Abstract:The present paper introduces concurrency-driven enhancements to the training algorithm for the Kolmogorov-Arnold networks (KANs) that is based on the Newton-Kaczmarz (NK) method. Prior research shows that KANs trained using the NK-based approach outperform classical neural networks (multilayer perceptrons - MLPs) both in terms of accuracy and training time. Up to now, the fundamental limitation of the algorithm has been the sequential computation of the updates - each update depends on the results of the previous step, obstructing parallelisation; even though parallelisation of some parts of the algorithm, such as the evaluation of the basis functions, has already been proposed and tested. However, substantial acceleration is achievable. Three complementary concurrency-driven novel strategies are proposed in the present paper: (i) a pre-training procedure tailored to the NK updates' structure, (ii) training on disjoint subsets of data together with models' merging, and (iii) a division-free customisation of the algorithm for field-programmable gate arrays (FPGAs), which is implemented and tested directly on the device. Computational experiments are used to assess the scalability and to compare the authors' KAN implementation with popular MLP packages. All presented experimental results are fully reproducible, with the complete source codes available online.
Machine Learning (cs.LG)
arXiv:2512.18921 [cs.LG]
(or arXiv:2512.18921v5 [cs.LG] for this version)
Full text under the publisher's open licence · 205 words
Related coverage
Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias
arXiv · Jun 17, 2026
Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias
arXiv · Sep 9, 2026
Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline Networks
arXiv · Sep 15, 2026
TravKAN: Fast and Interpretable Nonlinear Traversability Analysis with Kolmogorov-Arnold Networks
arXiv · Aug 4, 2026