paper-with-me

Papers

Degree-Optimized Cumulative Polynomial Kolmogorov-Arnold Networks

2025-05-21 · Mathew Vanherreweghe, Lirandë Pira, Patrick Rebentrost

We introduce cumulative polynomial Kolmogorov-Arnold networks (CP-KAN), a neural architecture combining Chebyshev polynomial basis functions and quadratic unconstrained binary optimization (QUBO). Our primary contribution involves reformulating the degree selection problem as a QUBO task, reducing the complexity from $O(D^N)$ to a single optimization step per layer. This approach enables efficient degree selection across neurons while maintaining computational tractability. The architecture performs well in regression tasks with limited data, showing good robustness to input scales and natural regularization properties from its polynomial basis. Additionally, theoretical analysis establishes connections between CP-KAN's performance and properties of financial time series. Our empirical validation across multiple domains demonstrates competitive performance compared to several traditional architectures tested, especially in scenarios where data efficiency and numerical stability are important. Our implementation, including strategies for managing computational overhead in larger networks is available in Ref.~\citep{cpkan_implementation}.

📄 PDF Abstract BibTeX arXiv:2505.15228

Code (0)

등록된 구현이 없습니다.

Tasks

Kolmogorov-Arnold Networks

Similar Papers 제목 키워드 기반

Kolmogorov-Arnold PointNet: Deep learning for prediction of fluid fields on irregular geometries

2024-08-06 · Ali Kashefi

Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to traditional Multilayer Perceptrons (MLPs) in deep learning. KANs have already been integrated into various architectures, such as convolutional…

Kolmogorov-Arnold Networks

Combinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks

2025-08-16 · Hoang-Thang Ta, Duy-Quy Thai, Phuong-Linh Tran-Thi arxiv

For years, many neural networks have been developed based on the Kolmogorov-Arnold Representation Theorem (KART), which was created to address Hilbert's 13th problem. Recently, relying on KART, Kolmogorov-Arnold Networks…

Computational Efficiency

Necessary and sufficient conditions for universality of Kolmogorov-Arnold networks

2026-04-26 · Vugar Ismailov arxiv

We analyze the universal approximation property of Kolmogorov-Arnold Networks (KANs) in terms of their edge functions. If these functions are all affine, then universality clearly fails. How many non-affine functions are…

PolyKAN: Efficient Fused GPU Operators for Polynomial Kolmogorov-Arnold Network Variants

2025-11-18 · Mingkun Yu, Heming Zhong, Dan Huang, Yutong Lu 외 arxiv

Kolmogorov-Arnold Networks (KANs) promise higher expressive capability and stronger interpretability than Multi-Layer Perceptron, particularly in the domain of AI for Science. However, practical adoption has been hindere…

Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation

2024-05-12 · Sidharth SS, Keerthana AR, Gokul R, Anas KP

Accurate approximation of complex nonlinear functions is a fundamental challenge across many scientific and engineering domains. Traditional neural network architectures, such as Multi-Layer Perceptrons (MLPs), often str…

Kolmogorov-Arnold Networks