Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks

• URL: http://arxiv.org/abs/2508.00247v1
• Date: Fri, 01 Aug 2025 01:16:09 GMT
• Title: Sinusoidal Approximation Theorem for Kolmogorov-Arnold Networks
• Authors: Sergei Gleyzer, Hanh Nguyen, Dinesh P. Ramakrishnan, Eric A. F. Reinhardt,
• Abstract summary: Kolmogorov-Arnold Networks (KANs) have been recently proposed as an alternative to multilayer perceptrons.<n>We propose a novel KAN variant by replacing both the inner and outer functions in the Kolmogorov-Arnold representation with weighted sinusoidal functions of learnable frequencies.<n>Inspired by simplifications introduced by Lorentz and Sprecher, we fix the phases of the sinusoidal activations to linearly spaced constant values and provide a proof of its theoretical validity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Kolmogorov-Arnold representation theorem states that any continuous multivariable function can be exactly represented as a finite superposition of continuous single variable functions. Subsequent simplifications of this representation involve expressing these functions as parameterized sums of a smaller number of unique monotonic functions. These developments led to the proof of the universal approximation capabilities of multilayer perceptron networks with sigmoidal activations, forming the alternative theoretical direction of most modern neural networks. Kolmogorov-Arnold Networks (KANs) have been recently proposed as an alternative to multilayer perceptrons. KANs feature learnable nonlinear activations applied directly to input values, modeled as weighted sums of basis spline functions. This approach replaces the linear transformations and sigmoidal post-activations used in traditional perceptrons. Subsequent works have explored alternatives to spline-based activations. In this work, we propose a novel KAN variant by replacing both the inner and outer functions in the Kolmogorov-Arnold representation with weighted sinusoidal functions of learnable frequencies. Inspired by simplifications introduced by Lorentz and Sprecher, we fix the phases of the sinusoidal activations to linearly spaced constant values and provide a proof of its theoretical validity. We also conduct numerical experiments to evaluate its performance on a range of multivariable functions, comparing it with fixed-frequency Fourier transform methods and multilayer perceptrons (MLPs). We show that it outperforms the fixed-frequency Fourier transform and achieves comparable performance to MLPs.

Related papers

• From Taylor Series to Fourier Synthesis: The Periodic Linear Unit [0.0]
  We introduce the Periodic Linear Unit (PLU), a learnable sine-wave based activation with periodic non-monotonicity.<n>We demonstrate that a minimal activation with only two neurons can solve the spiral classification task, a feat impossible for equivalent networks using standard activations.
  arXiv  Detail & Related papers  (2025-08-02T03:26:48Z)
• The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity [0.7499722271664144]
  We study how non-linear activation functions contribute to shaping neural networks' implicit bias.<n>We show that local dynamical attractors facilitate the formation of clusters of hyperplanes where the input to a neuron's activation function is zero.
  arXiv  Detail & Related papers  (2025-03-13T17:36:46Z)
• Robustifying Fourier Features Embeddings for Implicit Neural Representations [25.725097757343367]
  Implicit Neural Representations (INRs) employ neural networks to represent continuous functions by mapping coordinates to the corresponding values of the target function.<n>INRs face a challenge known as spectral bias when dealing with scenes containing varying frequencies.<n>We propose the use of multi-layer perceptrons (MLPs) without additive.
  arXiv  Detail & Related papers  (2025-02-08T07:43:37Z)
• State-Free Inference of State-Space Models: The Transfer Function Approach [132.83348321603205]
  State-free inference does not incur any significant memory or computational cost with an increase in state size. We achieve this using properties of the proposed frequency domain transfer function parametrization. We report improved perplexity in language modeling over a long convolutional Hyena baseline.
  arXiv  Detail & Related papers  (2024-05-10T00:06:02Z)
• EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention [88.45459681677369]
  We propose a novel transformer variant with complex vector attention, named EulerFormer. It provides a unified theoretical framework to formulate both semantic difference and positional difference. It is more robust to semantic variations and possesses moresuperior theoretical properties in principle.
  arXiv  Detail & Related papers  (2024-03-26T14:18:43Z)
• Enhancing Solutions for Complex PDEs: Introducing Complementary Convolution and Equivariant Attention in Fourier Neural Operators [17.91230192726962]
  We propose a novel hierarchical Fourier neural operator along with convolution-residual layers and attention mechanisms to solve complex PDEs. We find that the proposed method achieves superior performance in these PDE benchmarks, especially for equations characterized by rapid coefficient variations.
  arXiv  Detail & Related papers  (2023-11-21T11:04:13Z)
• Message-Passing Neural Quantum States for the Homogeneous Electron Gas [41.94295877935867]
  We introduce a message-passing-neural-network-based wave function Ansatz to simulate extended, strongly interacting fermions in continuous space. We demonstrate its accuracy by simulating the ground state of the homogeneous electron gas in three spatial dimensions.
  arXiv  Detail & Related papers  (2023-05-12T04:12:04Z)
• D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory [79.50644650795012]
  We propose a deep learning approach to solve Kohn-Sham Density Functional Theory (KS-DFT) We prove that such an approach has the same expressivity as the SCF method, yet reduces the computational complexity. In addition, we show that our approach enables us to explore more complex neural-based wave functions.
  arXiv  Detail & Related papers  (2023-03-01T10:38:10Z)
• Third quantization of open quantum systems: new dissipative symmetries and connections to phase-space and Keldysh field theory formulations [77.34726150561087]
  We reformulate the technique of third quantization in a way that explicitly connects all three methods. We first show that our formulation reveals a fundamental dissipative symmetry present in all quadratic bosonic or fermionic Lindbladians. For bosons, we then show that the Wigner function and the characteristic function can be thought of as ''wavefunctions'' of the density matrix.
  arXiv  Detail & Related papers  (2023-02-27T18:56:40Z)
• Fast Sampling of Diffusion Models via Operator Learning [74.37531458470086]
  We use neural operators, an efficient method to solve the probability flow differential equations, to accelerate the sampling process of diffusion models. Compared to other fast sampling methods that have a sequential nature, we are the first to propose a parallel decoding method. We show our method achieves state-of-the-art FID of 3.78 for CIFAR-10 and 7.83 for ImageNet-64 in the one-model-evaluation setting.
  arXiv  Detail & Related papers  (2022-11-24T07:30:27Z)
• Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces [52.424621227687894]
  We introduce a unified framework for group equivariant networks on homogeneous spaces. We take advantage of the sparsity of Fourier coefficients of the lifted feature fields. We show that other methods treating features as the Fourier coefficients in the stabilizer subgroup are special cases of our activation.
  arXiv  Detail & Related papers  (2022-06-16T17:59:01Z)
• First Power Linear Unit with Sign [0.0]
  It is enlightened by common inverse operation while endowed with an intuitive meaning of bionics. We extend the function presented to a more generalized type called PFPLUS with two parameters that can be fixed or learnable.
  arXiv  Detail & Related papers  (2021-11-29T06:47:58Z)
• An Investigation of Potential Function Designs for Neural CRF [75.79555356970344]
  In this paper, we investigate a series of increasingly expressive potential functions for neural CRF models. Our experiments show that the decomposed quadrilinear potential function based on the vector representations of two neighboring labels and two neighboring words consistently achieves the best performance.
  arXiv  Detail & Related papers  (2020-11-11T07:32:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.