A redistributed proximal bundle method for nonsmooth nonconvex functions with inexact information

In this paper, we propose a redistributed proximal bundle method for class of nonconvex nonsmooth optimization problems with inexact information, i.e., consider the problem computing approximate critical points when only information about function values and subgradients are available show that reasonable convergence properties obtained. We assume errors in computation functions bounded principle do not have to vanish within limits. For functions, design convexification technique, which ensures linearization error its augmentation is nonnegative. Meanwhile, utilize noise management strategies update parameters reduce impact information. Based on method, can obtain solution.