AI RESEARCH
PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
arXiv CS.LG
•
ArXi:2502.03749v2 Announce Type: replace Optimal transport (OT) is a widely used tool in machine learning, but computing high-accuracy solutions for large instances remains costly. Entropic regularization and the Sinkhorn algorithm improve scalability; however, when the regularization parameter is small, Sinkhorn convergence slows, and the iterates approach an entropic solution that remains separated from the true OT plan by an entropic-bias plateau. We