Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs

Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track

Bibtex Paper

Authors

Jacob Lindb├Ąck, Zesen Wang, Mikael Johansson

Abstract

We present an efficient algorithm for regularized optimal transport. In contrast toprevious methods, we use the Douglas-Rachford splitting technique to developan efficient solver that can handle a broad class of regularizers. The algorithmhas strong global convergence guarantees, low per-iteration cost, and can exploitGPU parallelization, making it considerably faster than the state-of-the-art formany problems. We illustrate its competitiveness in several applications, includingdomain adaptation and learning of generative models.