This paper improves the state-of-the-art rate of a first-order algorithm for solving entropy regularized optimal transport. The resulting rate for approximating the optimal transport (OT) has been improved from $\widetilde{{O}}({n^{2.5}}/{\epsilon})$ to $\widetilde{{O}}({n^2}/{\epsilon})$, where $n$ is the problem size and $\epsilon$ is the accuracy level. In particular, we propose an accelerated primal-dual stochastic mirror descent algorithm with variance reduction. Such special design helps us improve the rate compared to other accelerated primal-dual algorithms. We further propose a batch version of our stochastic algorithm, which improves the computational performance through parallel computing. To compare, we prove that the computational complexity of the Stochastic Sinkhorn algorithm is $\widetilde{{O}}({n^2}/{\epsilon^2})$, which is slower than our accelerated primal-dual stochastic mirror algorithm. Experiments are done using synthetic and real data, and the results match our theoretical rates. Our algorithm may inspire more research to develop accelerated primal-dual algorithms that have rate $\widetilde{{O}}({n^2}/{\epsilon})$ for solving OT.
翻译:本文改进了解决 entropy 正规化最佳运输的第一阶算法的先进速度。 因此, 接近最佳运输( OT) 的先进速度已经从 $@O ⁇ ( {\\ 2.5 ⁇ / ~ ~ ~ ~) 美元提高到 $\ 全局的 O ⁇ ( ({ \ 2} / ~ ~ ~ ~ ) 美元, 美元是问题大小, 美元是准确程度。 特别是, 我们提议加速初等和相近镜底偏移算法, 并减少差异。 这种特殊设计有助于我们提高最佳运输( OT) 的速度。 我们进一步提议了我们的随机算法的批量版本, 通过平行计算来提高计算绩效。 相比之下, 我们证明Sinkshinkhorn 算法的计算复杂性是 $\ $\\ ( \\ 2} ({ \ \ / ~ ~ ~ } { ~ } ( ~ ~ } } 美元, 我们提议加速的初等镜底级算算算算算算算算算法, 我们的模拟算算算算算算算算算算算算算算算得得更慢。