Reproduce “Optimal Feedback Communication via Posterior Matching” 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

Ofer Shayevitz, Meir Feder

Posterior matching uses noiseless feedback to turn the receiver’s uncertainty about a message into each next channel input. It evaluates the posterior percentile of the true message point and maps it through the inverse CDF of a chosen input distribution. For a binary symmetric channel, this is Horstein’s median rule, achieving every rate below capacity for all nontrivial crossover probabilities.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.