Reproduce “Deep Learning for Random Objects in Metric Spaces: Beyond Manifold Assumptions” 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
Marcos Matabuena, Xiaokai Luo, Oscar Hernan Madrid Padilla
The method predicts metric-space responses by estimating squared distances to observed responses with separate neural networks, then selecting the observed response with the smallest predicted distance. Simulations found lowest mean error at p=20 for q=2 across four training sizes in the tested settings, but KNN led at smaller p and usually at q=4.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.