Reproduce “Operator Learning of Microstructure-Dependent Internal-Variable Models for Inelastic Homogenization: Approximation and Complexity” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Lianghao Cao, George Stepaniants, Andrew M. Stuart
The authors model homogenized viscoelasticity with a recurrent neural operator, using microstructure-conditioned evolving internal variables instead of full loading history. They prove, under specified bounds, uniform stress approximation for periodic Kelvin–Voigt materials in dimensions one to three. In two-dimensional Voronoi tests, mean relative error falls from 5.6% with one variable to 2.9% with 25, versus about 25% for the memoryless model; these are empirical results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.