REVIEW 6 cited by
Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality
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
In this paper, we study the statistical limits of deep learning techniques for solving elliptic partial differential equations (PDEs) from random samples using the Deep Ritz Method (DRM) and Physics-Informed Neural Networks (PINNs). To simplify the problem, we focus on a prototype elliptic PDE: the Schr\"odinger equation on a hypercube with zero Dirichlet boundary condition, which has wide application in the quantum-mechanical systems. We establish upper and lower bounds for both methods, which improves upon concurrently developed upper bounds for this problem via a fast rate generalization bound. We discover that the current Deep Ritz Methods is sub-optimal and propose a modified version of it. We also prove that PINN and the modified version of DRM can achieve minimax optimal bounds over Sobolev spaces. Empirically, following recent work which has shown that the deep model accuracy will improve with growing training sets according to a power law, we supply computational experiments to show a similar behavior of dimension dependent power law for deep PDE solvers.
Forward citations
Cited by 6 Pith papers
-
Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method
Harmonic functions with Barron Dirichlet data fail to be Lipschitz or H², yet admit Barron approximants of norm ~|log ε| with error ~ε on half-spaces and 2D rectangles, giving Deep Ritz a priori rates.
-
Feature Learning for the High Dimensional Stationary Sch\"odinger Equation with Deep Ritz Method
Gradient descent on single-index and two-neuron models provably recovers feature directions of the Schrödinger equation source term in the deep Ritz framework.
-
Posterior Concentration of Bayesian Physics-Informed Neural Networks for Elliptic PDEs
Bayesian PINNs for elliptic PDEs have posteriors that contract around the true solution at near-optimal rates, with the prior adapting automatically to unknown smoothness.
-
Feature Learning for the High Dimensional Stationary Sch\"odinger Equation with Deep Ritz Method
For single- and two-index neural hypotheses in the deep Ritz method for the Schrödinger equation, gradient descent converges in O(log(1/ε)) iterations and the Ritz minimizer aligns with the source feature; a second fe...
-
Concentration Inequalities for Sample Cross-Covariances
Proves sharp operator-norm concentration and expectation bounds for sample cross-covariances of sub-Gaussian and Gaussian vectors, governed by effective ranks of the marginal covariances.
-
Unifying Learning Dynamics and Generalization in Transformers Scaling Law
Claims a two-stage transformer scaling law (exponential then C^{-1/6}) with matching bounds, but the lower bounds are missing, the exponent is inconsistent (-1/7 vs -1/6), and the law is an artifact of hand-set M = Θ(...
Discussion (0). Sign in to comment.