Back to Search
Start Over
Learning rates of gradient descent algorithm for classification
- Source :
-
Journal of Computational & Applied Mathematics . Feb2009, Vol. 224 Issue 1, p182-192. 11p. - Publication Year :
- 2009
-
Abstract
- Abstract: In this paper, a stochastic gradient descent algorithm is proposed for the binary classification problems based on general convex loss functions. It has computational superiority over the existing algorithms when the sample size is large. Under some reasonable assumptions on the hypothesis space and the underlying distribution, the learning rate of the algorithm has been established, which is faster than that of closely related algorithms. [Copyright &y& Elsevier]
Details
- Language :
- English
- ISSN :
- 03770427
- Volume :
- 224
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- Journal of Computational & Applied Mathematics
- Publication Type :
- Academic Journal
- Accession number :
- 35504251
- Full Text :
- https://doi.org/10.1016/j.cam.2008.04.022