Zobrazeno 1 - 10
of 429 117
pro vyhledávání: '"A Barron"'
Autor:
García, Jonathan, Petersen, Philipp
We prove that a classifier with a Barron-regular decision boundary can be approximated with a rate of high polynomial degree by ReLU neural networks with three hidden layers when a margin condition is assumed. In particular, for strong margin conditi
Externí odkaz:
http://arxiv.org/abs/2412.07312
Autor:
Francis, Leslie J.1,2 (AUTHOR) leslie.francis@warwick.ac.uk, Davis, Francis2 (AUTHOR), McKenna, Ursula2 (AUTHOR)
Publikováno v:
Mental Health, Religion & Culture. Aug2024, p1-17. 17p. 2 Charts.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
This paper presents a method for finding a sparse representation of Barron functions. Specifically, given an $L^2$ function $f$, the inverse scale space flow is used to find a sparse measure $\mu$ minimising the $L^2$ loss between the Barron function
Externí odkaz:
http://arxiv.org/abs/2312.02671
Autor:
Chung, Seok-Young, Sun, Qiyu
Graph convolutional neural network (GCNN) operates on graph domain and it has achieved a superior performance to accomplish a wide range of tasks. In this paper, we introduce a Barron space of functions on a compact domain of graph signals. We prove
Externí odkaz:
http://arxiv.org/abs/2311.02838
Autor:
Liao, Yulei, Ming, Pingbing
We prove the sharp embedding between the spectral Barron space and the Besov space. Given the spectral Barron space as the target function space, we prove a dimension-free result that if the neural network contains $L$ hidden layers with $N$ units pe
Externí odkaz:
http://arxiv.org/abs/2309.00788
Autor:
Wu, Lei
Publikováno v:
Journal of Machine Learning, 2023
An important problem in machine learning theory is to understand the approximation and generalization properties of two-layer neural networks in high dimensions. To this end, researchers have introduced the Barron space $\mathcal{B}_s(\Omega)$ and th
Externí odkaz:
http://arxiv.org/abs/2305.19082
The approximation properties of infinitely wide shallow neural networks heavily depend on the choice of the activation function. To understand this influence, we study embeddings between Barron spaces with different activation functions. These embedd
Externí odkaz:
http://arxiv.org/abs/2305.15839
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Abrahamsen, Nilin, Lin, Lin
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 neural network
Externí odkaz:
http://arxiv.org/abs/2303.12856