"A Dynamic Smoothing Technique for a Class of Nonsmooth Optimization Problems on Manifolds"Beck, AmirWe consider the problem of minimizing the sum of a smooth nonconvex function and a nonsmooth convex function over a compact embedded submanifold. We describe an algorithm, which we refer to as “dynamic smoothing gradient descent on manifolds” (DSGM), that is based on applying Riemmanian gradient steps on a series of smooth approximations of the objective function that are determined by a diminishing sequence of smoothing parameters. The DSGM algorithm is simple and can be easily employed to a broad class of problems without any complex adjustments. We show that all accumulation points of the sequence generated by the method are stationary. We devise a convergence rate of $O(1/k^{1/3})$ in terms of an optimality measure that can be easily computed. The talk is based on a joint work with Israel Rossett. |
« back