使用小波样基的Kolmogorov-Arnold网络(KAN/H)
KAN/H: Kolmogorov-Arnold Network using Haar-like bases
AI总结:
KAN/H通过使用Haar样分层基系统改进Kolmogorov-Arnold网络,实现高维函数逼近的高精度和低超参数调优需求。
摘要:
使用Haar基系统进行函数逼近在通过Patricia树压缩时提供高效的实现,同时保留了小波在全局和局部拟合中的灵活性。然而,与B样条逼近类似,在高维空间中实现高精度仍然具有挑战性。本文提出KAN/H,这是Kolmogorov-Arnold网络(KAN)的一种变体,使用具有非零一阶导数的Haar样分层基系统,而不是B样条。我们还提出了一种学习率调度方法和处理无界实值输入的方法,利用Haar样分层基的线性逼近性质。通过将所得到的算法应用于函数逼近问题和MNIST,我们确认我们的方法需要极少的问题特定超参数调优。
英文摘要:
Function approximation using Haar basis systems offers an efficient implementation when compressed via Patricia trees while retaining the flexibility of wavelets for both global and local fitting. However, like B-spline-based approximations, achieving high accuracy in high dimensions remains challenging. This paper proposes KAN/H, a variant of the Kolmogorov-Arnold Network (KAN) that uses a Haar-like hierarchical basis system with nonzero first-order derivatives, instead of B-splines. We also propose a learning-rate scheduling method and a method for handling unbounded real-valued inputs, leveraging properties of linear approximation with Haar-like hierarchical bases. By applying the resulting algorithm to function-approximation problems and MNIST, we confirm that our approach requires minimal problem-specific hyperparameter tuning.
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。