Bundle Methods for Machine Learning
Bundle Methods for Machine Learning
复制标题
DOI：
--
复制
发表时间：
2007-12
期刊：
影响因子：
--
通讯作者：
Alex Smola;S. Vishwanathan;Quoc V. Le
中科院分区：
文献类型：
--
作者：
Alex Smola;S. Vishwanathan;Quoc V. Le
我们提出了一个全局收敛的正则化风险最小化问题的方法。我们的方法适用于支持向量估计，回归，高斯过程，以及任何其他正则化风险最小化设置，导致凸优化问题。SVMPerf可以被证明是我们方法的一个特例。除了统一的框架，我们提出了严格的收敛界，这表明我们的算法收敛在O（1/<$）步骤一般凸问题和O（log（1/<$））步骤的连续可微问题的精度。我们在实验中证明了我们的方法的性能。
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.