We propose an alternating linearization bundle method for minimizing the sum of a nonconvex function and a convex function. The convex function is assumed to be "simple" in the sense that finding its proximal-like point is relatively easy. The nonconvex function is known through oracles which provide inexact information. The errors in function values and subgradient evaluations might be unknown, but are bounded by universal constants. We examine an alternating linearization bundle method in this setting and obtain reasonable convergence properties. Numerical results show the good performance of the method.

中文翻译：

---

一类具有不精确信息的非凸优化问题的交替线性化束方法

我们提出一种交替线性化束方法，以最小化非凸函数和凸函数的和。从发现其近端状点相对容易的意义上说，凸函数被认为是“简单的”。非凸函数是通过提供不精确信息的Oracle已知的。函数值和次梯度评估中的错误可能是未知的，但受通用常数限制。我们在这种情况下检查交替线性化束方法，并获得合理的收敛性。数值结果表明了该方法的良好性能。