A Stochastic Trust Region Method for Unconstrained Optimization Problems
Keyword(s):
In this paper, a stochastic trust region method is proposed to solve unconstrained minimization problems with stochastic objectives. Particularly, this method can be used to deal with nonconvex problems. At each iteration, we construct a quadratic model of the objective function. In the model, stochastic gradient is used to take the place of deterministic gradient for both the determination of descent directions and the approximation of the Hessians of the objective function. The behavior and the convergence properties of the proposed method are discussed under some reasonable conditions. Some preliminary numerical results show that our method is potentially efficient.
2011 ◽
Vol 18
(9)
◽
pp. 1303-1309
◽
2011 ◽
Vol 141
◽
pp. 92-97
2005 ◽
Vol 163
(1)
◽
pp. 489-504
◽
2005 ◽
Vol 19
(1-2)
◽
pp. 165-177
◽
2011 ◽
Vol 28
(05)
◽
pp. 585-600
◽
A New Nonmonotone Adaptive Retrospective Trust Region Method for Unconstrained Optimization Problems
2015 ◽
Vol 167
(2)
◽
pp. 676-692
◽
2009 ◽
Vol 232
(2)
◽
pp. 318-326
◽