论文标题
关于实用原始偶坐标方法的复杂性
On the Complexity of a Practical Primal-Dual Coordinate Method
论文作者
论文摘要
我们证明了具有随机外推和坐标下降（Pure-CD）的原始二重算法的复杂性界限，该算法已证明可以获得良好的实践性能，以求解双线性偶联的凸 - conconcove Min-Max问题。我们的复杂性范围要么匹配或改善文献中最著名的结果，要么稀疏和稀疏（强） - convex-（强烈） - 期权问题。
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.
