English
Related papers

Related papers: Kolmogorov--Arnold stability

200 papers

The Kolmogorov-Arnold (KA) representation theorem constructs universal, but highly non-smooth inner functions (the first layer map) in a single (non-linear) hidden layer neural network. Such universal functions have a distinctive local…

Machine Learning · Computer Science 2025-12-03 Michael H. Freedman , Michael Mulligan

There is a longstanding debate whether the Kolmogorov-Arnold representation theorem can explain the use of more than one hidden layer in neural networks. The Kolmogorov-Arnold representation decomposes a multivariate function into an…

Machine Learning · Computer Science 2021-01-05 Johannes Schmidt-Hieber

The Kolmogorov-Arnold Theorem (KAT), or more generally, the Kolmogorov Superposition Theorem (KST), establishes that any non-linear multivariate function can be exactly represented as a finite superposition of non-linear univariate…

Machine Learning · Computer Science 2025-06-17 Francesco Alesiani , Takashi Maruyama , Henrik Christiansen , Viktor Zaverkin

The Kolmogorov-Arnold representation is a proven adequate replacement of a continuous multivariate function by an hierarchical structure of multiple functions of one variable. The proven existence of such representation inspired many…

Optimization and Control · Mathematics 2020-06-23 Andrew Polar , Michael Poluektov

We show that for any finite-dimensional quantum systems the conserved quantities can be characterized by their robustness to small perturbations: for fragile symmetries small perturbations can lead to large deviations over long times, while…

Quantum Physics · Physics 2021-04-14 Daniel Burgarth , Paolo Facchi , Hiromichi Nakazato , Saverio Pascazio , Kazuya Yuasa

It is known that any continuous multivariate function can be represented exactly by a composition functions of a single variable - the so-called Kolmogorov-Arnold representation. It can be a convenient tool for tasks where it is required to…

Numerical Analysis · Mathematics 2025-02-04 Michael Poluektov , Andrew Polar

Kolmogorov-Arnold Networks (KANs) have recently emerged as a novel approach to function approximation, demonstrating remarkable potential in various domains. Despite their theoretical promise, the robustness of KANs under adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Tal Alter , Raz Lapid , Moshe Sipper

Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical expressiveness, they suffer from severe parameter explosion and limited ability to capture high-frequency features in high-dimensional tasks. To…

Machine Learning · Computer Science 2026-05-26 Jusheng Zhang , Yijia Fan , Kaitong Cai , Keze Wang , Wenhao Wang

The Kaczmarz algorithm (KA) is a popular method for solving a system of linear equations. In this note we derive a new exponential convergence result for the KA. The key allowing us to establish the new result is to rewrite the KA in such a…

Systems and Control · Computer Science 2015-06-23 Liang Dai , Thomas Schön

Kolmogorov and Arnold, in answering Hilbert's 13th problem (in the context of continuous functions), laid the foundations for the modern theory of Neural Networks (NNs). Their proof divides the representation of a multivariate function into…

Numerical Analysis · Mathematics 2024-10-14 Michael H. Freedman

Kolmogorov-Arnold Networks (KANs) offer a structured and interpretable framework for multivariate function approximation by composing univariate transformations through additive or multiplicative aggregation. This paper establishes…

Machine Learning · Computer Science 2025-12-05 Wei Liu , Eleni Chatzi , Zhilu Lai

Exterior powers play important roles in persistent homology in computational geometry. In the present paper we study the problem of extracting the $K$ longest intervals of the exterior-power layers of a tame persistence module. We prove a…

Computational Geometry · Computer Science 2025-12-24 Yoshihiro Maruyama

We study the stability and breakup of invariant tori in Hamiltonian flows using a combination of Kolmogorov-Arnold-Moser (KAM) theory and renormalization-group techniques. We implement the scheme numerically for a family of Hamiltonians…

chao-dyn · Physics 2009-10-31 M. Govin , C. Chandre , H. R. Jauslin

This article is about the proof of the celebrated KAM theorem as sketched out in \cite{KOL} Kolmogorov's original presentation to the ICM. The proof presented here has been detailed as an effort to clarify if Kolmogorov's argument can be…

Dynamical Systems · Mathematics 2023-04-25 Othmane Islah

In the paper, we prove an abstract KAM (Kolmogorov-Arnold-Moser) theorem for infinite dimensional reversible systems. Using this KAM theorem, we obtain the existence and linear stability of quasi-periodic solutions for a class of reversible…

Dynamical Systems · Mathematics 2019-03-19 Yingnan Sun , Zhaowei Lou , Jiansheng Geng

This is part II of our book on KAM theory. We start by defining functorial analysis and then switch to the particular case of Kolmogorov spaces. We develop functional calculus based on the notion of local operators. This allows to define…

Dynamical Systems · Mathematics 2018-09-12 Mauricio Garay , Duco van Straten

Our understanding of the mechanisms governing the structure and secular evolution galaxies assume nearly integrable Hamiltonians with regular orbits; our perturbation theories are founded on the averaging theorem for isolated resonances. On…

Astrophysics of Galaxies · Physics 2015-08-28 Martin D. Weinberg

Eliasson and Kuksin developed a KAM approach to study the persistence of the invariant tori for nonlinear Schr\"{o}dinger equation on $\mathbb{T}^{d}$. In this note, we improve Eliasson and Kuksin's KAM theorem by using Kolmogorov's…

Analysis of PDEs · Mathematics 2021-05-27 Xiaolong He , Jia Shi , Xiaoping Yuan

Church-Ellenberg-Farb used the language of FI-modules to prove that the cohomology of certain sequences of hyperplane arrangements with S_n-actions satisfies representation stability. Here we lift their results to the level of the…

Geometric Topology · Mathematics 2016-06-13 Nir Gadish

The relationship between overparameterization, stability, and generalization remains incompletely understood in the setting of discontinuous classifiers. We address this gap by establishing a generalization bound for finite function classes…

Machine Learning · Computer Science 2026-03-04 Jonas von Berg , Adalbert Fono , Massimiliano Datres , Sohir Maskey , Gitta Kutyniok
‹ Prev 1 2 3 10 Next ›