Article ID: | iaor201526020 |
Volume: | 229 |
Issue: | 1 |
Start Page Number: | 759 |
End Page Number: | 769 |
Publication Date: | Jun 2015 |
Journal: | Annals of Operations Research |
Authors: | Wang Qi |
Keywords: | optimization, heuristics |
For many popular stochastic approximation algorithms, such as the stochastic gradient method and the simultaneous perturbation stochastic approximation method, the practical gain sequence selection is different from the optimal selection, that is theoretically derived from asymptotical performance. We provide formal justification for the reasons why we choose such gain sequence in practice.