Dual variational neural network decouples p-Laplace into linear Poisson and divergence-free minimization subproblems approximated by two NNs, with error analysis from vector inequalities and statistical learning theory, showing robust convergence for p near 1 and large p.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
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 feature emerges as regularization varies.
citing papers explorer
-
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 feature emerges as regularization varies.