Reproduce “Clifford Neural Layers for PDE Modeling” 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
Johannes Brandstetter, Rianne van den Berg, Max Welling, Jayesh K. Gupta
The authors develop Clifford neural layers that represent related scalar, vector, and higher-order field components together in PDE surrogates. Clifford convolutions and Fourier operations act on multivectors rather than treating components as scalar channels. On 3D Maxwell prediction with 640 training trajectories, CFNO lowers five-step rollout SMSE versus FNO, but shallow-water results show this advantage is not universal.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.