We prove complexity bounds for the primal-dual algorithm with random extrapolation and coordinate descent (PURE-CD), which has been shown to obtain good practical performance for solving convex-concave min-max problems with bilinear coupling. Our complexity bounds either match or improve the best-known results in the literature for both dense and sparse (strongly)-convex-(strongly)-concave problems.
翻译:我们用随机外推法来证明原始双向算法的复杂性界限。 事实证明,这种算法在解决双线联结的细小问题上取得了良好的实际表现。 我们的复杂界限要么匹配,要么改进了文献中最著名的关于密密密(强)混结(强)和(强)混杂(强)混结)问题的结果。