Reproduce “Schrödinger-Bass Bridge Barycenter Models for Measure-Valued Data” 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
Ngoc-Hai Nguyen, Thuan Nguyen, Prakash Ishwar, Shuchin Aeron
The authors introduce Schrödinger–Bass Bridge barycenters to estimate a shared source or intermediate distribution from observed populations. The method controls both directed drift and diffusive volatility, with decoder, encoder, symmetric, and Markovian formulations. In tests, decoder SBB reduced MNIST latent-source W2 error to 0.79 ± 0.09 versus 0.99 ± 0.11 for debiased Sinkhorn; results vary by condition and metric.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.