Nonlocal techniques for the analysis of deep ReLU neural network approximations

• URL: http://arxiv.org/abs/2504.04847v1
• Date: Mon, 07 Apr 2025 09:00:22 GMT
• Title: Nonlocal techniques for the analysis of deep ReLU neural network approximations
• Authors: Cornelia Schneider, Mario Ullrich, Jan Vybiral,
• Abstract summary: Recently, Daubechies, DeVore, Foucart, Hanin, and Petrova introduced a system of piece-wise linear functions.<n>We show that this system serves as a Riesz basis also for Sobolev spaces and Barron classes.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, Daubechies, DeVore, Foucart, Hanin, and Petrova introduced a system of piece-wise linear functions, which can be easily reproduced by artificial neural networks with the ReLU activation function and which form a Riesz basis of $L_2([0,1])$. This work was generalized by two of the authors to the multivariate setting. We show that this system serves as a Riesz basis also for Sobolev spaces $W^s([0,1]^d)$ and Barron classes ${\mathbb B}^s([0,1]^d)$ with smoothness $0<s<1$. We apply this fact to re-prove some recent results on the approximation of functions from these classes by deep neural networks. Our proof method avoids using local approximations and allows us to track also the implicit constants as well as to show that we can avoid the curse of dimension. Moreover, we also study how well one can approximate Sobolev and Barron functions by ANNs if only function values are known.

Related papers

• Dimension-independent learning rates for high-dimensional classification problems [53.622581586464634]
  We show that every $RBV2$ function can be approximated by a neural network with bounded weights. We then prove the existence of a neural network with bounded weights approximating a classification function.
  arXiv  Detail & Related papers  (2024-09-26T16:02:13Z)
• On the optimal approximation of Sobolev and Besov functions using deep ReLU neural networks [2.4112990554464235]
  We show that the rate $mathcalO((WL)-2s/d)$ indeed holds under the Sobolev embedding condition. Key tool in our proof is a novel encoding of sparse vectors by using deep ReLU neural networks with varied width and depth.
  arXiv  Detail & Related papers  (2024-09-02T02:26:01Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Efficient uniform approximation using Random Vector Functional Link networks [0.0]
  A Random Vector Functional Link (RVFL) network is a depth-2 neural network with random inner nodes and biases. We show that an RVFL with ReLU activation can approximate the Lipschitz target function. Our method of proof is rooted in theory and harmonic analysis.
  arXiv  Detail & Related papers  (2023-06-30T09:25:03Z)
• Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces [2.7195102129095003]
  Deep neural networks with the ReLU activation function can approximate functions in the Sobolev spaces $Ws(L_q(Omega))$ and Besov spaces $Bs_r(L_q(Omega))$. This problem is important when studying the application of neural networks in a variety of fields.
  arXiv  Detail & Related papers  (2022-11-25T23:32:26Z)
• Shallow neural network representation of polynomials [91.3755431537592]
  We show that $d$-variables of degreeR$ can be represented on $[0,1]d$ as shallow neural networks of width $d+1+sum_r=2Rbinomr+d-1d-1d-1[binomr+d-1d-1d-1[binomr+d-1d-1d-1[binomr+d-1d-1d-1d-1[binomr+d-1d-1d-1d-1
  arXiv  Detail & Related papers  (2022-08-17T08:14:52Z)
• Expressive power of binary and ternary neural networks [91.3755431537592]
  We show that deep sparse ReLU networks with ternary weights and deep ReLU networks with binary weights can approximate $beta$-H"older functions on $[0,1]d$.
  arXiv  Detail & Related papers  (2022-06-27T13:16:08Z)
• Deep neural network approximation of analytic functions [91.3755431537592]
  entropy bound for the spaces of neural networks with piecewise linear activation functions. We derive an oracle inequality for the expected error of the considered penalized deep neural network estimators.
  arXiv  Detail & Related papers  (2021-04-05T18:02:04Z)
• Nonclosedness of Sets of Neural Networks in Sobolev Spaces [0.0]
  We show that realized neural networks are not closed in order-$(m-1)$ Sobolev spaces $Wm-1,p$ for $p in [1,infty]$. For a real analytic activation function, we show that sets of realized neural networks are not closed in $Wk,p$ for any $k in mathbbN$.
  arXiv  Detail & Related papers  (2020-07-23T00:57:25Z)
• Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions [84.49087114959872]
  We provide the first non-asymptotic analysis for finding stationary points of nonsmooth, nonsmooth functions. In particular, we study Hadamard semi-differentiable functions, perhaps the largest class of nonsmooth functions.
  arXiv  Detail & Related papers  (2020-02-10T23:23:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.