Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods
This provides a scalable solution for applications relying on optimal transport, though it is incremental as it builds on existing first-order optimization methods.
The paper tackles the problem of efficiently computing optimal transport distances between distributions, achieving a runtime of O~(n^2/ε) for ε additive accuracy, which is state-of-the-art among first-order methods and shows favorable numerical performance compared to classical algorithms like Sinkhorn and Greenkhorn.
Efficient computation of the optimal transport distance between two distributions serves as an algorithm subroutine that empowers various applications. This paper develops a scalable first-order optimization-based method that computes optimal transport to within $\varepsilon$ additive accuracy with runtime $\widetilde{O}( n^2/\varepsilon)$, where $n$ denotes the dimension of the probability distributions of interest. Our algorithm achieves the state-of-the-art computational guarantees among all first-order methods, while exhibiting favorable numerical performance compared to classical algorithms like Sinkhorn and Greenkhorn. Underlying our algorithm designs are two key elements: (a) converting the original problem into a bilinear minimax problem over probability distributions; (b) exploiting the extragradient idea -- in conjunction with entropy regularization and adaptive learning rates -- to accelerate convergence.