Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport
This work offers incremental improvements to existing algorithms like Sinkhorn and MultiSinkhorn for computational optimal transport problems.
The authors tackled the problem of solving regularized multimarginal optimal transport by proposing a batch version of the Greenkhorn algorithm, providing a global linear convergence rate and explicit iteration complexity bounds.
In this work we propose a batch version of the Greenkhorn algorithm for multimarginal regularized optimal transport problems. Our framework is general enough to cover, as particular cases, some existing algorithms like Sinkhorn and Greenkhorn algorithm for the bi-marginal setting, and (greedy) MultiSinkhorn for multimarginal optimal transport. We provide a complete convergence analysis, which is based on the properties of the iterative Bregman projections (IBP) method with greedy control. Global linear rate of convergence and explicit bound on the iteration complexity are obtained. When specialized to above mentioned algorithms, our results give new insights and/or improve existing ones.