论文标题
在线不可知论的多类提升
Online Agnostic Multiclass Boosting
论文作者
论文摘要
提升是机器学习中的一种基本方法，既享有强大的理论和实践保证。在高级，增强算法巧妙地汇总了弱学习者，以任意高精度生成预测。通过这种方式，将算法提高算法转换为强大的学习者。最近，Brukhim等人。扩展到在线不可知论二进制分类设置。其方法中的一种关键要素是简单简单地简单地简化在线凸优化，该优化有效地将任意在线凸优化器转换为不可知论的在线助推器。在这项工作中，我们将此减少扩展到多类问题，并为在线不可知论杂种分类提供了第一个增强算法。我们的减少还可以构建用于统计不可知论，在线可实现和统计可实现的多类促进的算法。
Boosting is a fundamental approach in machine learning that enjoys both strong theoretical and practical guarantees. At a high-level, boosting algorithms cleverly aggregate weak learners to generate predictions with arbitrarily high accuracy. In this way, boosting algorithms convert weak learners into strong ones. Recently, Brukhim et al. extended boosting to the online agnostic binary classification setting. A key ingredient in their approach is a clean and simple reduction to online convex optimization, one that efficiently converts an arbitrary online convex optimizer to an agnostic online booster. In this work, we extend this reduction to multiclass problems and give the first boosting algorithm for online agnostic mutliclass classification. Our reduction also enables the construction of algorithms for statistical agnostic, online realizable, and statistical realizable multiclass boosting.
