Reproduce “Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions” 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
Ha Dang, Sebastian Schmidt, Juergen Hesser
Cut-DeepONet represents discontinuous PDE solutions by predicting cut locations, lifting each side into a separately labelled smooth piece, and learning those pieces with a neural operator. On linear advection, it reports lower global and local errors than FNO; it leads on both metrics for inviscid Burgers’. For cardiac cells, its global error is lowest, but FNO’s local error is lower.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.