Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs
This provides a faster solution for applications like domain adaptation and generative model learning, though it appears incremental as it builds on existing splitting techniques.
The authors tackled the problem of regularized optimal transport by developing an efficient solver using the Douglas-Rachford splitting technique, which is considerably faster than state-of-the-art methods and can exploit GPU parallelization.
We present an efficient algorithm for regularized optimal transport. In contrast to previous methods, we use the Douglas-Rachford splitting technique to develop an efficient solver that can handle a broad class of regularizers. The algorithm has strong global convergence guarantees, low per-iteration cost, and can exploit GPU parallelization, making it considerably faster than the state-of-the-art for many problems. We illustrate its competitiveness in several applications, including domain adaptation and learning of generative models.