Adaptive Subgrad
Technion - Israel Institute of TechnologyGoogleUniversity of California (UC) BerkeleyText classification
Developed by Technion - Israel Institute of Technology,Google,University of California (UC) Berkeley in 2011, Adaptive Subgrad is a text classification model.
About Adaptive Subgrad
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradient-based learning. Metaphorically, the adaptation allows us to find nee
Details
- Provider
- Technion - Israel Institute of Technology,Google,University of California (UC) Berkeley
- Task
- Text classification
- Released
- 2011-10-03