Convex Equilibrium Potentials for Monge--Amp\`ere: Curvature Bounds and A Posteriori Evaluation

2026-10-23来源 arXiv cs.NAEnglish

arXiv:2610.31386v1 Announce Type: new Abstract: Equilibrium neural networks define their hidden state as the fixed point of a contraction, so their effective depth is set at evaluation time rather than by the architecture. Using them for fully nonlinear PDEs raises two issues that explicit networks avoid: second derivatives may grow with the effective depth, and the potential is only ever evaluated approximately. We study nonnegative softplus equilibrium networks with contraction factor $q

原文：https://www.a8q9.cn/en/article/convex-equilibrium-potentials-for-monge-amp-ere-curvature-bounds-and-a-posterior-6b9f7f.html

Convex Equilibrium Potentials for Monge--Amp\`ere: Curvature Bounds and A Posteriori Evaluation

相关文章