3 search results - page 1 / 1 » Proximal regularization for online and batch learning |
ICML
2009
IEEE
14 years 5 months ago
2009
IEEE
Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
NIPS
2001
13 years 6 months ago
2001
Abstract--Kernel-based algorithms such as support vector machines have achieved considerable success in various problems in batch setting, where all of the training data is availab...
ACL
2009
13 years 2 months ago
2009
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...