Reproduce “Kernel Integrated $R^2$: A Measure of Dependence” 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
Pouya Roudaki, Shakeel Gavioli-Akilagun, Florian Kalinke, Mona Azadkia, Zoltán Szabó
The authors introduce a kernel-based dependence measure for structured outcomes and propose graph and RKHS estimators. The measure uses locally normalized response variation and is directional, with values of zero at independence and one when the response is almost surely a measurable function of covariates. In tested simulations, both estimators have higher independence-test power than competitors, limited to those settings.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.