AI RESEARCH
Robust Sublinear Convergence Rates for Iterative Bregman Projections
arXiv CS.LG
•
ArXi:2602.01372v2 Announce Type: replace-cross Entropic regularization provides a simple way to approximate linear programs whose constraints split into two or tractable blocks. The resulting objectives are amenable to cyclic Kullback-Leibler (KL) Bregman projections, with Sinkhorn-type algorithms for optimal transport, matrix scaling, and barycenters as canonical examples. This paper gives a general blueprint for proving $O(1/k)$ dual convergence rate with a constant that scales only linearly in $1/\gamma$, where $\gamma$ is the entropic regularization parameter.