arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2503.23038cs.LG

基于Kolmogorov-Arnold定理与核函数的函数拟合

Function Fitting Based on Kolmogorov-Arnold Theorem and Kernel Functions

XJTLU(西交利物浦大学)

Jianpeng Liu, Qizhi Pan

AI总结:

本文基于Kolmogorov-Arnold定理与核方法提出统一框架,将KAN与自注意力统一为核函数线性组合,并设计低秩Pseudo-MHSA(参数减少近50%)及Gaussian-MHSA,在CIFAR-10上取得与ViT相当的性能。

摘要:

本文提出一个基于Kolmogorov-Arnold表示定理与核方法的统一理论框架。通过分析核函数、Kolmogorov-Arnold网络(KANs)中的B样条基函数以及自注意力机制中内积运算之间的数学关系,我们建立了一个基于核的特征拟合框架,将这两种模型统一为核函数的线性组合。在该框架下,我们提出一个低秩伪多头自注意力模块(Pseudo-MHSA),将传统MHSA的参数数量减少了近50%。此外,我们设计了一个高斯核多头自注意力变体(Gaussian-MHSA),以验证非线性核函数在特征提取中的有效性。在CIFAR-10数据集上的实验表明,在MAE框架下,Pseudo-MHSA模型取得了与同维度ViT模型相当的性能,且可视化分析揭示了它们多头分布模式的相似性。我们的代码已公开。

英文摘要:

This paper proposes a unified theoretical framework based on the Kolmogorov-Arnold representation theorem and kernel methods. By analyzing the mathematical relationship among kernels, B-spline basis functions in Kolmogorov-Arnold Networks (KANs) and the inner product operation in self-attention mechanisms, we establish a kernel-based feature fitting framework that unifies the two models as linear combinations of kernel functions. Under this framework, we propose a low-rank Pseudo-Multi-Head Self-Attention module (Pseudo-MHSA), which reduces the parameter count of traditional MHSA by nearly 50\%. Furthermore, we design a Gaussian kernel multi-head self-attention variant (Gaussian-MHSA) to validate the effectiveness of nonlinear kernel functions in feature extraction. Experiments on the CIFAR-10 dataset demonstrate that Pseudo-MHSA model achieves performance comparable to the ViT model of the same dimensionality under the MAE framework and visualization analysis reveals their similarity of multi-head distribution patterns. Our code is publicly available.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑