Bundle Methods for Machine Learning

We present a globally convergent method for regularized risk minimization problems. Our method applies to Support Vector estimation, regression, Gaussian Processes, and any other regularized risk minimization setting which leads to a convex optimization problem. SVMPerf can be shown to be a special case of our approach. In addition to the unified framework we present tight convergence bounds, which show that our algorithm converges in O(1/ ) steps to precision for general convex problems and in O(log(1/ )) steps for continuously differentiable problems. We demonstrate in experiments the performance of our approach.

• Type: Conference
• Year: 2007
• Where: NIPS
• Authors: Alex J. Smola, S. V. N. Vishwanathan, Quoc V. Le
• Keywords: Convex Optimization Problem, Information Technology, NIPS 2007, Regularized Risk Minimization, Risk Minimization Problems