arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14987math.OC
收藏

0/1损失光滑牛顿法的平方收敛性Optimization

Quadratic Convergence of Smoothing Newton's Method for 0/1 Loss Optimization

Shenglong Zhou, Lili Pan, Naihua Xiu, Houduo Qi

摘要:

0/1损失函数是对分类误差进行建模的最自然的选择之一,并且它具有广泛的应用,包括支持向量机和1位压缩感知。由于0/1损失函数的组合性质,基于凸松弛或平滑近似的方法已经主导了现有的研究,并且通常能够提供良好质量的近似解。然而,这些方法不是直接优化0/1损失函数,因此没有为原始问题建立最优性。本文研究0/1函数极小化的最优性条件,并首次提出了在合理的条件下直接优化0/1函数的局部平方收敛的牛顿法。大量的数值实验表明其优越的性能,因为人们会期望从牛顿型方法。大量的数值实验表明其优越的性能,因为人们会期望从牛顿型方法。

英文摘要:

It has been widely recognized that the 0/1 loss function is one of the most natural choices for modelling classification errors, and it has a wide range of applications including support vector machines and 1-bit compressed sensing. Due to the combinatorial nature of the 0/1 loss function, methods based on convex relaxations or smoothing approximations have dominated the existing research and are often able to provide approximate solutions of good quality. However, those methods are not optimizing the 0/1 loss function directly and hence no optimality has been established for the original problem. This paper aims to study the optimality conditions of the 0/1 function minimization, and for the first time to develop Newton's method that directly optimizes the 0/1 function with a local quadratic convergence under reasonable conditions. Extensive numerical experiments demonstrate its superior performance as one would expect from Newton-type methods.ions. Extensive numerical experiments demonstrate its superior performance as one would expect from Newton-type methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑