论文标题
一种随机凸复合优化的单切近端束法
A single cut proximal bundle method for stochastic convex composite optimization
论文作者
论文摘要
本文考虑了优化问题，其中目标是预期和封闭凸复合函数给出的函数的总和，并提出了用于解决它的随机复合近端束（SCPB）方法。为他们建立复杂性保证，而无需了解与问题实例相关的参数。此外，可以证明当已知这些问题参数时，它们具有最佳的复杂性。据我们所知，这是能够处理连续分布的随机编程的第一个近端捆绑方法。最后，我们提出的计算结果表明，在考虑的所有情况下，SCPB基本上优于鲁棒随机近似（RSA）方法。
This paper considers optimization problems where the objective is the sum of a function given by an expectation and a closed convex composite function, and proposes stochastic composite proximal bundle (SCPB) methods for solving it. Complexity guarantees are established for them without requiring knowledge of parameters associated with the problem instance. Moreover, it is shown that they have optimal complexity when these problem parameters are known. To the best of our knowledge, this is the first proximal bundle method for stochastic programming able to deal with continuous distributions. Finally, we present computational results showing that SCPB substantially outperforms the robust stochastic approximation (RSA) method in all instances considered.
