Elliptic energy loses coercivity on neural ansatzes due to manifold non-closedness and condensation, but state functions remain bounded and converge strongly, with rates proved for Gaussian wave-packet approximations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
The Coercivity Gap in Neural PDE Solvers: Parameter Escape and Functional Convergence
Elliptic energy loses coercivity on neural ansatzes due to manifold non-closedness and condensation, but state functions remain bounded and converge strongly, with rates proved for Gaussian wave-packet approximations.