English
Related papers

Related papers: Evidence for a Functional Proximity Law in Multila…

200 papers

Several recent works have shown separation results between deep neural networks, and hypothesis classes with inferior approximation capacity such as shallow networks or kernel classes. On the other hand, the fact that deep networks can…

Machine Learning · Computer Science 2021-07-20 Eran Malach , Gilad Yehudai , Shai Shalev-Shwartz , Ohad Shamir

In recent years, fake news detection has received increasing attention in public debate and scientific research. Despite advances in detection techniques, the production and spread of false information have become more sophisticated, driven…

Computation and Language · Computer Science 2026-03-27 Pietro Dell'Oglio , Alessandro Bondielli , Francesco Marcelloni , Lucia C. Passaro

Most social, technological and biological networks are embedded in a finite dimensional space, and the distance between two nodes influences the likelihood that they link to each other. Indeed, in social systems, the chance that two…

Physics and Society · Physics 2018-06-27 Paul Balister , Chaoming Song , Oliver Riordan , Bela Bollobas , Albert-Laszlo Barabasi

Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the activation function, feedforward neural networks are dense in broad function…

Machine Learning · Computer Science 2026-05-21 Soumendu Sundar Mukherjee , Himasish Talukdar

Network representations of systems from various scientific and societal domains are neither completely random nor fully regular, but instead appear to contain recurring structural building blocks. These features tend to be shared by…

Social and Information Networks · Computer Science 2016-10-20 Ian Barnett , Nishant Malik , Marieke L. Kuijjer , Peter J. Mucha , Jukka-Pekka Onnela

We prove a negative result for the approximation of functions defined on compact subsets of $\mathbb{R}^d$ (where $d \geq 2$) using feedforward neural networks with one hidden layer and arbitrary continuous activation function. In a…

Machine Learning · Computer Science 2020-08-26 J. M. Almira , P. E. Lopez-de-Teruel , D. J. Romero-Lopez , F. Voigtlaender

We consider continuous relational structures with finite domain $[n] := \{1, \ldots, n\}$ and a many valued logic, $CLA$, with values in the unit interval and which uses continuous connectives and continuous aggregation functions. $CLA$…

Logic in Computer Science · Computer Science 2026-05-28 Vera Koponen

Knowledge of the domain of applicability of a machine learning model is essential to ensuring accurate and reliable model predictions. In this work, we develop a new and general approach of assessing model domain and demonstrate that our…

Materials Science · Physics 2025-03-25 Lane E. Schultz , Yiqi Wang , Ryan Jacobs , Dane Morgan

The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation…

Machine Learning · Computer Science 2016-08-12 Hrushikesh Mhaskar , Tomaso Poggio

In this short note, we give an elementary proof of a universal approximation theorem for neural networks with three hidden layers and increasing, continuous, bounded activation function. The result is weaker than the best known results, but…

Machine Learning · Computer Science 2024-12-24 Chris Monico

A key element of understanding the efficacy of overparameterized neural networks is characterizing how they represent functions as the number of weights in the network approaches infinity. In this paper, we characterize the norm required to…

Machine Learning · Computer Science 2019-10-04 Greg Ongie , Rebecca Willett , Daniel Soudry , Nathan Srebro

In recent years, there has been considerable innovation in the world of predictive methodologies. This is evident by the relative domination of machine learning approaches in various classification competitions. While these algorithms have…

Machine Learning · Statistics 2020-10-12 Barinder Thind , Kevin Multani , Jiguo Cao

The approximation power of general feedforward neural networks with piecewise linear activation functions is investigated. First, lower bounds on the size of a network are established in terms of the approximation error and network depth…

Machine Learning · Computer Science 2018-07-02 Mohammad Mehrabi , Aslan Tchamkerten , Mansoor I. Yousefi

In this paper we initiate the study of \emph{property testing of weighted computational networks viewed as computational devices}. Our goal is to design property testing algorithms that for a given computational network with oracle access…

Data Structures and Algorithms · Computer Science 2025-12-09 Artur Czumaj , Christian Sohler

The classical Universal Approximation Theorem holds for neural networks of arbitrary width and bounded depth. Here we consider the natural `dual' scenario for networks of bounded width and arbitrary depth. Precisely, let $n$ be the number…

Machine Learning · Computer Science 2020-06-09 Patrick Kidger , Terry Lyons

The principle of similarity, or homophily, is often used to explain patterns observed in complex networks such as transitivity and the abundance of triangles (3-cycles). However, many phenomena from division of labor to protein-protein…

Physics and Society · Physics 2022-10-12 Szymon Talaga , Andrzej Nowak

Persistent Homology (PH) has been successfully used to train networks to detect curvilinear structures and to improve the topological quality of their results. However, existing methods are very global and ignore the location of topological…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Doruk Oner , Adélie Garin , Mateusz Koziński , Kathryn Hess , Pascal Fua

Protein-protein interactions can be properly modeled as scale-free complex networks, while the lethality of proteins has been correlated with the node degrees, therefore defining a lethality-centrality rule. In this work we revisit this…

Disordered Systems and Neural Networks · Physics 2007-05-23 Luciano da Fontoura Costa , Francisco Aparecido Rodrigues , Gonzalo Travieso

Overparameterized neural networks enjoy great representation power on complex data, and more importantly yield sufficiently smooth output, which is crucial to their generalization and robustness. Most existing function approximation…

Machine Learning · Statistics 2022-06-10 Hao Liu , Minshuo Chen , Siawpeng Er , Wenjing Liao , Tong Zhang , Tuo Zhao

While the universal approximation property holds both for hierarchical and shallow networks, we prove that deep (hierarchical) networks can approximate the class of compositional functions with the same accuracy as shallow networks but with…

Machine Learning · Computer Science 2016-05-31 Hrushikesh Mhaskar , Qianli Liao , Tomaso Poggio