A monotonic ICNN architecture with domain reduction to the positive octant approximates polyconvex envelopes of isotropic functions more efficiently than existing necessary-and-sufficient methods, demonstrated on Saint Venant-Kirchhoff energy.
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
Mesoscale crystal plasticity simulations with GND length-scale hardening capture experimentally observed finite-width adiabatic shear bands and dislocation patterning in polycrystals up to very large strains without softening.
citing papers explorer
-
Compression of Polyconvex Envelopes of Isotropic Functions via Monotonic Input Convex Neural Networks
A monotonic ICNN architecture with domain reduction to the positive octant approximates polyconvex envelopes of isotropic functions more efficiently than existing necessary-and-sufficient methods, demonstrated on Saint Venant-Kirchhoff energy.