English
Related papers

Related papers: Layer-wise Lipschitz-Product Control for Deep Kolm…

200 papers

We investigate the integration of Kolmogorov-Arnold Networks (KANs) into hard-constrained recurrent physics-informed architectures (HRPINN) to evaluate the fidelity of learned residual manifolds in oscillatory systems. Motivated by the…

Machine Learning · Computer Science 2026-03-06 Enzo Nicolas Spotorno , Josafat Leal Filho , Antonio Augusto Medeiros Frohlich

Hyperspectral image classification is a crucial but challenging task due to the high dimensionality and complex spatial-spectral correlations inherent in hyperspectral data. This paper employs Wavelet-based Kolmogorov-Arnold Network…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Seyd Teymoor Seydi , Zavareh Bozorgasl , Hao Chen

Kolmogorov-Arnold Neural Networks (KANs) have gained significant attention in the machine learning community. However, their implementation often suffers from poor training stability and heavy trainable parameter. Furthermore, there is…

Machine Learning · Computer Science 2025-01-17 Liangwewi Nathan Zheng , Wei Emma Zhang , Lin Yue , Miao Xu , Olaf Maennel , Weitong Chen

Complex dynamical systems governed by holomorphic maps such as $z^2 + c$ exhibit fractal boundaries with extreme sensitivity to initial conditions. Accurately modelling these structures from data requires methods that respect the underlying…

Machine Learning · Computer Science 2026-05-22 Bhaskar Ranjan Karn , Dinesh Kumar

Kolmogorov-Arnold Networks (KANs) have recently emerged as a compelling alternative to multilayer perceptrons, offering enhanced interpretability via functional decomposition. However, existing KAN architectures, including spline-,…

Machine Learning · Computer Science 2026-02-19 Sidharth S. Menon , Ameya D. Jagtap

Lipschitz Bound Estimation is an effective method of regularizing deep neural networks to make them robust against adversarial attacks. This is useful in a variety of applications ranging from reinforcement learning to autonomous systems.…

Machine Learning · Computer Science 2022-07-18 Sarosij Bose

The widespread use of Multi-layer perceptrons (MLPs) often relies on a fixed activation function (e.g., ReLU, Sigmoid, Tanh) for all nodes within the hidden layers. While effective in many scenarios, this uniformity may limit the networks…

Machine Learning · Computer Science 2025-04-28 Hy Nguyen , Duy Khoa Pham , Srikanth Thudumu , Hung Du , Rajesh Vasa , Kon Mouzakis

We propose PO-CKAN, a physics-informed deep operator framework based on Chunkwise Rational Kolmogorov--Arnold Networks (KANs), for approximating the solution operators of partial differential equations. This framework leverages a Deep…

Machine Learning · Computer Science 2025-11-04 Junyi Wu , Guang Lin

We introduce Kolmogorov--Arnold Neural Operator (KANO), a dual-domain neural operator jointly parameterized by both spectral and spatial bases with intrinsic symbolic interpretability. We theoretically demonstrate that KANO overcomes the…

Machine Learning · Computer Science 2026-02-26 Jin Lee , Ziming Liu , Xinling Yu , Yixuan Wang , Haewon Jeong , Murphy Yuezhen Niu , Zheng Zhang

Kolmogorov-Arnold Networks (KAN) are a new class of neural network architecture representing a promising alternative to the Multilayer Perceptron (MLP), demonstrating improved expressiveness and interpretability. However, KANs suffer from…

Machine Learning · Computer Science 2025-03-04 Cale Coffman , Lizhong Chen

We show that \emph{efficient Turing computability} at any fixed input/output precision implies the existence of \emph{compositionally sparse} (bounded-fan-in, polynomial-size) DAG representations and of corresponding neural approximants…

Machine Learning · Computer Science 2025-10-15 Tomaso Poggio

In this paper, we determine analytical bounds on the local Lipschitz constants of of affine functions composed with rectified linear units (ReLUs). Affine-ReLU functions represent a widely used layer in deep neural networks, due to the fact…

Machine Learning · Computer Science 2020-08-17 Trevor Avant , Kristi A. Morgansen

This paper introduces a new parameterization of deep neural networks (both fully-connected and convolutional) with guaranteed $\ell^2$ Lipschitz bounds, i.e. limited sensitivity to input perturbations. The Lipschitz guarantees are…

Machine Learning · Computer Science 2023-06-07 Ruigang Wang , Ian R. Manchester

We prove Carl's type inequalities for the error of approximation of compact sets K by deep and shallow neural networks. This in turn gives lower bounds on how well we can approximate the functions in K when requiring the approximants to…

Machine Learning · Statistics 2022-12-06 Guergana Petrova , Przemysław Wojtaszczyk

The purpose of this article is to develop a machinery to study the capacity of deep neural networks (DNNs) to approximate high-dimensional functions. In particular, we show that DNNs have the expressive power to overcome the curse of…

Numerical Analysis · Mathematics 2026-04-30 Pierfrancesco Beneventano , Patrick Cheridito , Robin Graeber , Arnulf Jentzen , Benno Kuckuck

This paper introduces a novel application of Kolmogorov-Arnold Networks (KANs) to time series forecasting, leveraging their adaptive activation functions for enhanced predictive modeling. Inspired by the Kolmogorov-Arnold representation…

Signal Processing · Electrical Eng. & Systems 2025-10-28 Cristian J. Vaca-Rubio , Luis Blanco , Roberto Pereira , Màrius Caus

Kolmogorov-Arnold Networks (KANs) have recently emerged as a powerful architecture for various machine learning applications. However, their unique structure raises significant concerns regarding their computational overhead. Existing…

Machine Learning · Computer Science 2026-04-07 Bilal Khalid , Pedro Freire , Sergei K. Turitsyn , Jaroslaw E. Prilepsky

We propose a novel layer-wise parameterization for convolutional neural networks (CNNs) that includes built-in robustness guarantees by enforcing a prescribed Lipschitz bound. Each layer in our parameterization is designed to satisfy a…

Machine Learning · Computer Science 2026-04-10 Patricia Pauli , Ruigang Wang , Ian Manchester , Frank Allgöwer

Artificial Neural Networks (ANNs) have significantly advanced various fields by effectively recognizing patterns and solving complex problems. Despite these advancements, their interpretability remains a critical challenge, especially in…

Machine Learning · Computer Science 2025-11-24 Alejandro Polo-Molina , David Alfaya , Jose Portela

In this paper, we consider the problem of automatically designing a Rectified Linear Unit (ReLU) Neural Network (NN) architecture (number of layers and number of neurons per layer) with the assurance that it is sufficiently parametrized to…

Machine Learning · Computer Science 2021-09-22 James Ferlez , Yasser Shoukry