On the local convergence of a stochastic semismooth Newton method for nonsmooth nonconvex optimization
On the local convergence of a stochastic semismooth Newton method for nonsmooth nonconvex optimization
复制标题
非光滑非凸优化的随机半光滑牛顿法的局部收敛性
DOI：
10.1007/s11425-020-1865-1
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Michael Ulbrich
中科院分区：
文献类型：
--
作者：
Andre Milzarek;Xiantao Xiao;Zaiwen Wen;Michael Ulbrich
In this work, we present probabilistic local convergence results for a stochastic semismooth Newton method for a class of stochastic composite optimization problems involving the sum of smooth nonconvex and nonsmooth convex terms in the objective function. We assume that the gradient and Hessian information of the smooth part of the objective function can only be approximated and accessed via calling stochastic first- and second-order oracles. The approach combines stochastic semismooth Newton steps, stochastic proximal gradient steps and a globalization strategy based on growth conditions. We present tail bounds and matrix concentration inequalities for the stochastic oracles that can be utilized to control the approximation errors via appropriately adjusting or increasing the sampling rates. Under standard local assumptions, we prove that the proposed algorithm locally turns into a pure stochastic semismooth Newton method and converges r-linearly or r-superlinearly with high probability.
登录
查看更多内容
DOI：
10.1287/moor.18.1.227
发表时间：
1993-02
期刊：
Math. Oper. Res.
影响因子：
--
作者：
L. Qi
通讯作者：
L. Qi
影响因子：
2.5
作者：
E. Ziegel
通讯作者：
E. Ziegel
DOI：
10.1007/b97543
发表时间：
2003
期刊：
--
影响因子：
--
作者：
F. Facchinei;J. Pang
通讯作者：
F. Facchinei;J. Pang
DOI：
10.1137/130936361
发表时间：
2013-09
期刊：
SIAM J. Optim.
影响因子：
--
作者：
Cong D. Dang;Guanghui Lan
通讯作者：
Cong D. Dang;Guanghui Lan
DOI：
10.1287/ijoo.2019.0043
发表时间：
2021-01
期刊：
INFORMS J. Optim.
影响因子：
--
作者：
Z. Yao;Peng Xu;Fred Roosta;Michael W. Mahoney
通讯作者：
Z. Yao;Peng Xu;Fred Roosta;Michael W. Mahoney