Reproduce “Improving Hamiltonian Learning through Local Energy Decomposition” 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
Yaojun Li, Yulong Yang, Christine Allen-Blanchette
The authors introduce LM-HNN, a Hamiltonian neural network that represents kinetic and potential energy as shared functions of local variable groups at multiple neighborhood sizes. It differentiates the learned energy to predict dynamics. In an eight-site spring chain, it recovers 99% of a force perturbation at wavenumber four, versus 26% for conventional HNN, but degrades at finer tested scales.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.