共 26 条
Approaching nonsmooth nonconvex minimization through second-order proximal-gradient dynamical systems
被引:16
作者:
Bot, Radu Ioan
[1
]
Csetnek, Ernoe Robert
[1
]
Laszlo, Szilard Csaba
[2
]
机构:
[1] Univ Vienna, Fac Math, Oskar Morgenstern Pl 1, A-1090 Vienna, Austria
[2] Tech Univ Cluj Napoca, Dept Math, Memorandumului 28, Cluj Napoca, Romania
基金:
奥地利科学基金会;
关键词:
Second-order dynamical system;
Nonsmooth nonconvex optimization;
Limiting subdifferential;
Kurdyka-ojasiewicz property;
MAXIMAL MONOTONE-OPERATORS;
CONVERGENCE;
ALGORITHMS;
INCLUSIONS;
D O I:
10.1007/s00028-018-0441-7
中图分类号:
O29 [应用数学];
学科分类号:
070104 ;
摘要:
We investigate the asymptotic properties of the trajectories generated by a second-order dynamical system of proximal-gradient type stated in connection with the minimization of the sum of a nonsmooth convex and a (possibly nonconvex) smooth function. The convergence of the generated trajectory to a critical point of the objective is ensured provided a regularization of the objective function satisfies the Kurdyka-ojasiewicz property. We also provide convergence rates for the trajectory formulated in terms of the ojasiewicz exponent.
引用
收藏
页码:1291 / 1318
页数:28
相关论文