REVIEW 3 cited by
Nearly Optimal Approximation Rates for Deep Super ReLU Networks on Sobolev Spaces
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
abstract
This paper introduces deep super ReLU networks (DSRNs) as a method for approximating functions in Sobolev spaces measured by Sobolev norms $W^{m,p}$ for $m\in\mathbb{N}$ with $m\ge 2$ and $1\le p\le +\infty$. Standard ReLU deep neural networks (ReLU DNNs) cannot achieve this goal. DSRNs consist primarily of ReLU DNNs, and several layers of the square of ReLU added at the end to smooth the networks output. This approach retains the advantages of ReLU DNNs, leading to the straightforward training. The paper also proves the optimality of DSRNs by estimating the VC-dimension of higher-order derivatives of DNNs, and obtains the generalization error in Sobolev spaces via an estimate of the pseudo-dimension of higher-order derivatives of DNNs.
Forward citations
Cited by 3 Pith papers
-
$\mathcal{C}^1$-approximation with rational functions and rational neural networks
C^1 approximation of Hölder functions by rational functions and rational neural networks is proven with rate N^{-(β-1)}, via a new rational approximation of ReQU.
-
An Imbalanced Learning-based Sampling Method for Physics-informed Neural Networks
RSmote uses SMOTE oversampling of high-residual points to train physics-informed neural networks with lower memory use and comparable accuracy to RAD.
-
Learn Singularly Perturbed Solutions via Homotopy Dynamics
A homotopy continuation method that starts training at a large PDE parameter and tracks the solution to small values improves neural network solvers for singularly perturbed problems.
Discussion (0). Continue with ORCID to comment.