REVIEW 5 cited by
Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory
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
read the original abstract
The problem of solving partial differential equations (PDEs) can be formulated into a least-squares minimization problem, where neural networks are used to parametrize PDE solutions. A global minimizer corresponds to a neural network that solves the given PDE. In this paper, we show that the gradient descent method can identify a global minimizer of the least-squares optimization for solving second-order linear PDEs with two-layer neural networks under the assumption of over-parametrization. We also analyze the generalization error of the least-squares optimization for second-order linear PDEs and two-layer neural networks, when the right-hand-side function of the PDE is in a Barron-type space and the least-squares optimization is regularized with a Barron-type norm, without the over-parametrization assumption.
Forward citations
Cited by 5 Pith papers
-
Is the neural tangent kernel of PINNs deep learning general partial differential equations always convergent ?
For PINNs solving general PDEs, the neural tangent kernel converges only if the network's output scaling exponent is large enough, with the threshold set by the homogeneity degree of the differential operator.
-
Optimization and generalization analysis for two-layer physics-informed neural networks without over-parametrization
A two-layer PINN can be trained by SGD to O(epsilon) loss with width independent of the number of samples, provided the target lies in a custom function class and the SGD trajectory does not explode.
-
Layer Separation Deep Learning Model with Auxiliary Variables for Partial Differential Equations
LySep separates the layers and derivatives of a PINN into auxiliary variables, yielding a shallow, easier-to-optimize loss that remains provably consistent with the original PINN loss.
-
Approximation Rates in Fr\'echet Metrics: Barron Spaces, Paley-Wiener Spaces, and Fourier Multipliers
Two theorems give sufficient shallow-network width to reach a prescribed error in a Fréchet metric of semi-norms, applied to exponential spectral Barron, Gelfand-Shilov, and bandlimited (Paley-Wiener type) symbol classes.
-
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.