Reproduce “Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey” 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
Abdelwahed Khamis, Russell Tsuchida, Mohamed Tarek, Vivien Rolland, Lars Petersson
The authors survey optimal transport and present a taxonomy of five ways to scale computation: simplifying measures, structuring the plan, approximating costs, partitioning computation, and accelerating solvers. Their focus is computational rather than statistical complexity. The survey reports that quantized Gromov-Wasserstein scales to datasets of up to 1 million points, with representative selection depending on the data.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.