Composite Objective Mirror Descent

We present a new method for regularized convex optimization and analyze it under both online and stochastic optimization settings. In addition to unifying previously known firstorder algorithms, such as the projected gradient method, mirror descent, and forwardbackward splitting, our method yields new analysis and algorithms. We also derive specific instantiations of our method for commonly used regularization functions, such as 1, mixed norm, and trace-norm.

• Type: Journal
• Year: 2010
• Where: COLT
• Authors: John Duchi, Shai Shalev-Shwartz, Yoram Singer, Ambuj Tewari
• Keywords: COLT 2010, Convex Optimization, Gradient Method, Machine Learning, Regularization Functions