Reproduce “Robust Reconstruction on Trees with a Growing Alphabet” 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
Heon Lee
The authors study root reconstruction from depth-k_q labels on Galton–Watson trees with a growing alphabet. They use repeated labels in separate child-subtrees to identify ancestry, while controlling collisions. As q tends to infinity, under dλ>1 and the stated depth, moment, and noise assumptions, noisy and noiseless posteriors converge in expected total variation, so Bayes accuracies share a limit bounded away from zero.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.