Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

April 2015, Vol. 27, No. 4, Pages 982-1004
(doi: 10.1162/NECO_a_00710)
© 2015 Massachusetts Institute of Technology
A Study on the Optimal Double Parameters for Steepest Descent with Momentum
Article PDF (201.38 KB)
Abstract

This letter presents the stability analysis for two steepest descent algorithms with momentum for quadratic functions. The corresponding local optimal parameters in Torii and Hagan (2002) and Zhang (2013) are extended to the global optimal parameters, that is, both the optimal learning rates and the optimal momentum factors are obtained simultaneously which make for the fastest convergence.