In this paper, we show that the bundle method can be applied to solve semidefinite programming problems with a low rank solution without ever constructing a full matrix. To accomplish this, we use recent results from randomly sketching matrix optimization problems and from the analysis of bundle methods. Under strong duality and strict complementarity of SDP, our algorithm produces primal and the dual sequences converging in feasibility at a rate of $\tilde{O}(1/\epsilon)$ and in optimality at a rate of $\tilde{O}(1/\epsilon^2)$. Moreover, our algorithm outputs a low rank representation of its approximate solution with distance to the optimal solution at most $O(\sqrt{\epsilon})$ within $\tilde{O}(1/\epsilon^2)$ iterations.
翻译:在本文中,我们展示了捆绑方法可以用来解决半无限期的编程问题,而没有建立完整的矩阵。为了实现这一点,我们使用了随机草图矩阵优化问题和捆绑方法分析的最新结果。在SDP的强大双重性和严格的互补性下,我们的算法产生原始和双重序列,其可行性以$\tilde{O}(1/\epsilon)$(1/\epsilon)的速率和以$\tilde{O}(1/\epsilon_2)的速率优化。此外,我们的算法输出出其近似解决方案的低等级代表值,在最高为$O(sqrt~epsilon}) 和$(1/\epsilon>2) 的迭代尔值内,其接近最佳解决方案的距离为$O(sqrt~) 。