Home » Publication » 27071

Dettaglio pubblicazione

2022, Proceedings of the 39th International Conference on Machine Learning, Pages - (volume: 162)

Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity (04b Atto di convegno in volume)

Kostic ́ Vladimir R., Salzo Saverio, Pontil Massimiliano

In this work we propose a batch multimarginal version of the Greenkhorn algorithm for the entropic-regularized optimal transport problem. This framework is general enough to cover, as par- ticular cases, existing Sinkhorn and Greenkhorn algorithms for the bi-marginal setting, and greedy MultiSinkhorn for the general multimarginal case. We provide a comprehensive convergence analy- sis based on the properties of the iterative Breg- man projections method with greedy control. Lin- ear rate of convergence as well as explicit bounds on the iteration complexity are obtained. When specialized to the above mentioned algorithms, our results give new convergence rates or provide key improvements over the state-of-the-art rates. We present numerical experiments showing that the flexibility of the batch can be exploited to im- prove performance of Sinkhorn algorithm both in bi-marginal and multimarginal settings.
Gruppo di ricerca: Continuous Optimization
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma