Reproduce “Stochastic Wasserstein Barycenters” 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
Sebastian Claici, Edward Chien, Justin Solomon
The authors define a Wasserstein barycenter for aggregating distributions while preserving their geometric arrangement of probability mass. Their sample-based method represents the result with finitely many points and optimizes their locations, avoiding a fixed output grid and density access. In a synthetic two-square example, it recovers the known uniform midpoint, unlike a comparison output; this does not establish general exact recovery.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.