Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
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...
Jyrki Kivinen, Alex J. Smola, Robert C. Williamson
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...