SVM optimization: inverse dependence on training set size

We discuss how the runtime of SVM optimization should decrease as the size of the training data increases. We present theoretical and empirical results demonstrating how a simple subgradient descent approach indeed displays such behavior, at least for linear kernels.

• Type: Conference
• Year: 2008
• Where: ICML
• Authors: Shai Shalev-Shwartz, Nathan Srebro
• Keywords: ICML 2008, Machine Learning, Subgradient Descent Approach, Training Data Increases