AI RESEARCH

Accelerated Sinkhorn Algorithms for Partial Optimal Transport

arXiv CS.LG

ArXi:2601.17196v3 Announce Type: replace Partial Optimal Transport (POT) addresses the problem of transporting only a fraction of the total mass between two distributions, making it suitable when marginals have unequal size or contain outliers. While Sinkhorn-based methods are widely used, their complexity bounds for POT remain suboptimal and can limit scalability. We