arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.00693stat.MLcs.LG
收藏

基于极大极小概率变换的监督分类

Supervised classification via minimax probabilistic transformations

BCAM-Basque Center of Applied Mathematics(BCAM巴斯克应用数学中心);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院)

Santiago Mazuelas, Andrea Zanoni, Aritz Perez

摘要:

用于监督分类的常规技术约束所考虑的分类规则,并且使用用于分类0-1损失的替代损失。分类规则的Festival族是那些享有适合于代理损失最小化的参数表示和适合于过拟合控制的低复杂度特性的分类规则。本文提出了基于鲁棒风险最小化(RRM)的分类技术,我们称之为线性概率分类器(LPC)。所提出的技术考虑无约束的分类规则,优化分类0-1损失,并在学习过程中提供性能界限。LPC通过使用线性优化来实现有效的学习,并通过使用RRM在多面体不确定性分布集上避免过度拟合。我们还提供了有限样本的泛化界的LPC,并显示其竞争力的性能与国家的最先进的技术,使用基准数据集。

英文摘要:

Conventional techniques for supervised classification constrain the classification rules considered and use surrogate losses for classification 0-1 loss. Favored families of classification rules are those that enjoy parametric representations suitable for surrogate loss minimization, and low complexity properties suitable for overfitting control. This paper presents classification techniques based on robust risk minimization (RRM) that we call linear probabilistic classifiers (LPCs). The proposed techniques consider unconstrained classification rules, optimize the classification 0-1 loss, and provide performance bounds during learning. LPCs enable efficient learning by using linear optimization, and avoid overffiting by using RRM over polyhedral uncertainty sets of distributions. We also provide finite-sample generalization bounds for LPCs and show their competitive performance with state-of-the-art techniques using benchmark datasets.

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。

↑