A Class of Hybrid Projection Methods with Perturbations - Advanced Research on Computer Education, Simulation and Modeling - page 225

Acknowledgments. This research is supported by the National Natural Science
Foundation of China (10901096) and the Natural Science Foundation of Shandong
Province (ZR2009AL019) and the Project of Shandong Province Higher Educational
Science and Technology Program (J09LA53).
References
[1] Bertsekas, D.P.: Nonlinear Programing. Athena Scientific, Belmont (1995)
[2] Bertsekas, D.P., Tsitsiklis, J.N.: Neuro-Dynamic programming. Athena Scientific,
Belmont (1996)
[3] Gaivoronski, A.A.: Convergence properties of backpropagation for neural nets via theory
of stochastic gradient methods. Part 1, Optim. Methods Software 4, 117-134 (1994)
[4] Grippo, L., Lampariello, F., Lucidi, S.: A nonmonotone line search technique for Newton's
method. SIAM J. Numer. Anal. 4, 707-716 (1986)
[5] Li, M., Wang, C.: Convergence property of gradient-type methods with non-monotone line
search in the presence of perturbation. Appl. Math. Optim. 174, 854-868 (2006)
[6] Shi, Z., Shen, J.: Convergence of nonmontone line search method. J. Comput. Appl.
Math. 193, 397-412 (2006)
[7] Wang, Y., Xiu, N.: Nonlinear Programming Theory and Algorithms. Shanxi Science and
Technology Press (2004)
[8] Yuan, Y., Sun, W.: Optimization Theory and Algorithms. Science Press, Beijing (1997)