Reproduce “Deep Neural Operator Learning for stochastic heat equations and applications” 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
Hengrong Du, Qi Feng, Weinan Wang
The authors construct a branch–trunk neural operator for stochastic heat equations, encoding initial data by point samples and distribution-valued Gaussian forcing by finite Fourier measurements. They bound truncation error using equation stability and prove path approximation in the space–time supremum norm, uniformly over Lipschitz initial data and for each fixed finite moment. Counts are theoretical and require a positive forcing-regularity gap.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.