Reproduce “Physics-informed machine learning as a kernel method” 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
Nathan Doumèche, Francis Bach, Gérard Biau, Claire Boyer
The authors study regression with noisy measurements and an imperfect physical law by penalizing both function roughness and the law’s differential residual. They show this estimator is a reproducing-kernel method, enabling error bounds. In a one-dimensional derivative example, squared prediction error decreases at rates n^-1 or n^-2/3 up to logarithms, with slopes -1.02 and -0.77, but no no-physics ablation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.