Accelerating adaptive online learning by matrix approximation

International Journal of Data Science and Analytics, pp. 389-400, 2020.

Cited by: 1|Bibtex|Views26|DOI:https://doi.org/10.1007/s41060-019-00174-4
EI
Other Links: dblp.uni-trier.de|link.springer.com

Abstract:

Adaptive subgradient methods are able to leverage the second-order information of functions to improve the regret and have become popular for online learning and optimization. According to the amount of information used, these methods can be divided into diagonal-matrix version (ADA-DIAG) and full-matrix version (ADA-FULL). In practice, A...More

Code:

Data:

Your rating :
0

 

Tags
Comments