English
Related papers

Related papers: Does the Barron space really defy the curse of dim…

200 papers

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as…

Machine Learning · Computer Science 2023-10-26 Leonardo Petrini

In this paper, we establish a neural network to approximate functionals, which are maps from infinite dimensional spaces to finite dimensional spaces. The approximation error of the neural network is $O(1/\sqrt{m})$ where $m$ is the size of…

Numerical Analysis · Mathematics 2023-01-02 Yahong Yang , Yang Xiang

In this work, we consider the approximation capabilities of shallow neural networks in weighted Sobolev spaces for functions in the spectral Barron space. The existing literature already covers several cases, in which the spectral Barron…

Machine Learning · Computer Science 2024-11-07 Ahmed Abdeljawad , Thomas Dittrich

The paper characterizes classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for…

Machine Learning · Computer Science 2017-02-07 Tomaso Poggio , Hrushikesh Mhaskar , Lorenzo Rosasco , Brando Miranda , Qianli Liao

We show that deep neural networks (DNNs) can efficiently learn any composition of functions with bounded $F_{1}$-norm, which allows DNNs to break the curse of dimensionality in ways that shallow networks cannot. More specifically, we derive…

Machine Learning · Statistics 2025-03-07 Arthur Jacot , Seok Hoan Choi , Yuxiao Wen

It is generally assumed that the brain uses something akin to sparse distributed representations. These representations, however, are high-dimensional and consequently they affect classification performance of traditional Machine Learning…

Neural and Evolutionary Computing · Computer Science 2022-08-29 Maria Osório , Luís Sa-Couto , Andreas Wichert

We study the approximation complexity of high-dimensional second-order elliptic PDEs with homogeneous boundary conditions on the unit hypercube, within the framework of Barron spaces. Under the assumption that the coefficients belong to…

Numerical Analysis · Mathematics 2025-10-21 Ziang Chen , Liqiang Huang

Artificial neural networks (ANNs) have become a very powerful tool in the approximation of high-dimensional functions. Especially, deep ANNs, consisting of a large number of hidden layers, have been very successfully used in a series of…

Numerical Analysis · Mathematics 2021-03-09 Philipp Grohs , Shokhrukh Ibragimov , Arnulf Jentzen , Sarah Koppensteiner

A burgeoning line of research leverages deep neural networks to approximate the solutions to high dimensional PDEs, opening lines of theoretical inquiry focused on explaining how it is that these models appear to evade the curse of…

Machine Learning · Computer Science 2023-03-28 Tanya Marwah , Zachary C. Lipton , Jianfeng Lu , Andrej Risteski

The curse of dimensionality poses a significant challenge to modern multilayer perceptron-based architectures, often causing performance stagnation and scalability issues. Addressing this limitation typically requires vast amounts of data.…

Machine Learning · Computer Science 2024-11-19 Divesh Basina , Joseph Raj Vishal , Aarya Choudhary , Bharatesh Chakravarthi

One of the key issues in the analysis of machine learning models is to identify the appropriate function space and norm for the model. This is the set of functions endowed with a quantity which can control the approximation and estimation…

Machine Learning · Computer Science 2021-03-30 Weinan E , Chao Ma , Lei Wu

A fundamental problem in quantum physics is to encode functions that are completely anti-symmetric under permutations of identical particles. The Barron space consists of high-dimensional functions that can be parameterized by infinite…

Numerical Analysis · Mathematics 2023-03-24 Nilin Abrahamsen , Lin Lin

We prove that the gradient descent training of a two-layer neural network on empirical or population risk may not decrease population risk at an order faster than $t^{-4/(d-2)}$ under mean field scaling. Thus gradient descent training for…

Machine Learning · Computer Science 2020-05-22 Stephan Wojtowytsch , Weinan E

Universal approximation theorems show that neural networks can approximate any continuous function; however, the number of parameters may grow exponentially with the ambient dimension, so these results do not fully explain the practical…

Machine Learning · Computer Science 2026-01-15 Changhoon Song , Seungchan Ko , Youngjoon Hong

We prove the sharp embedding between the spectral Barron space and the Besov space with embedding constants independent of the input dimension. Given the spectral Barron space as the target function space, we prove a dimension-free…

Numerical Analysis · Mathematics 2025-07-16 Yulei Liao , Pingbing Ming

High-dimensional data and high-dimensional representations of reality are inherent features of modern Artificial Intelligence systems and applications of machine learning. The well-known phenomenon of the "curse of dimensionality" states:…

Machine Learning · Computer Science 2020-01-22 Alexander N. Gorban , Valery A. Makarov , Ivan Y. Tyukin

We prove bounds for the approximation and estimation of certain binary classification functions using ReLU neural networks. Our estimation bounds provide a priori performance guarantees for empirical risk minimization using networks of a…

Functional Analysis · Mathematics 2022-03-11 Andrei Caragea , Philipp Petersen , Felix Voigtlaender

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

Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks as the curse of dimensionality (CoD) cannot be evaded when trying to approximate even a single ReLU neuron…

Machine Learning · Statistics 2024-06-27 Fanghui Liu , Leello Dadi , Volkan Cevher

We study the natural function space for infinitely wide two-layer neural networks with ReLU activation (Barron space) and establish different representation formulae. In two cases, we describe the space explicitly up to isomorphism. Using a…

Machine Learning · Statistics 2021-06-07 Weinan E , Stephan Wojtowytsch
‹ Prev 1 2 3 10 Next ›