arXiv:2606. 17927v2 Announce Type: replace-cross Abstract: Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional multilayer perceptrons by replacing linear weights with learnable univariate functions.
By Julian Hoever, Gregor Schiele
arXiv:2512. 12850v3 Announce Type: replace-cross Abstract: Low-latency, resource-efficient neural network inference on FPGAs is essential for applications demanding real-time capability and low power.
By Duc Hoang, Aarush Gupta, Philip Harris
arXiv:2512. 09084v3 Announce Type: replace Abstract: The Kolmogorov-Arnold representation theorem offers a theoretical alternative to Multi-Layer Perceptrons (MLPs) by placing learnable univariate functions on edges rather than nodes.
By Oscar Eliasson
arXiv:2607. 13413v1 Announce Type: cross Abstract: This study presents an empirical benchmarking comparison between Kolmogorov-Arnold Networks (KANs) and Multi-Layer Perceptrons (MLPs) on structured tabular classification tasks.
By Matthew Steven P. Toledo, Justine Raphael H. Jacinto, Vivekjeet Singh Chambal, Rodolfo C. Camaclang III, Jamlech Iram N. Gojo Cruz, Reginald Neil C. Recario
This study presents an empirical benchmarking comparison between Kolmogorov-Arnold Networks (KANs) and Multi-Layer Perceptrons (MLPs) on structured tabular classification tasks. Motivated by the growing interest in KANs as an alternative function-approximating architecture, we evaluate their out-of-the-box performance on twelve publicly available datasets spanning binary, multiclass, multilabel, and ordinal problems.
The paper reports an empirical scalability study of data‑parallel training for Kolmogorov‑Arnold Networks (KANs) on high‑performance computing systems. Using up to eight NVIDIA A100 GPUs across four nodes on the FinisTerrae III supercomputer, the authors evaluate strong and weak scaling, communication overhead, and model‑size scaling, finding a 74.7% parallel efficiency and a 5.97× speedup at eight GPUs. They observe non‑monotonic communication costs driven by All‑Reduce choices and inter‑node latency, and note that while the parameter‑to‑memory ratio improves with larger models, training time scales less favorably, leading to guidelines for GPU topology and model‑size selection.
By Guangneng Chen, David Garcia Selfa, Pablo Quesada Barriuso