论文标题
通过遗憾最小化在线不可知论
Online Agnostic Boosting via Regret Minimization
论文作者
论文摘要
增强是一种基于汇总弱学习规则的想法的广泛使用的机器学习方法。尽管在统计学习中，在可实现的和不可知的环境中都存在许多增强方法，但在在线学习中，它们仅在可实现的情况下才存在。在这项工作中，我们提供了第一个不可知论的在线增强算法；也就是说，鉴于一个弱者的学习者只有比遗憾的遗憾要少得多，我们的算法将其促进了一个以统一的遗憾的强大学习者。 我们的算法基于摘要（简单）简化为在线凸优化的优化，该优化有效地将任意的在线凸优化器转换为在线助推器。 此外，这种减少范围扩展到统计以及在线可实现的设置，从而统一了4个统计/在线和不可知论/可实现的提升案例。
Boosting is a widely used machine learning approach based on the idea of aggregating weak learning rules. While in statistical learning numerous boosting methods exist both in the realizable and agnostic settings, in online learning they exist only in the realizable case. In this work we provide the first agnostic online boosting algorithm; that is, given a weak learner with only marginally-better-than-trivial regret guarantees, our algorithm boosts it to a strong learner with sublinear regret. Our algorithm is based on an abstract (and simple) reduction to online convex optimization, which efficiently converts an arbitrary online convex optimizer to an online booster. Moreover, this reduction extends to the statistical as well as the online realizable settings, thus unifying the 4 cases of statistical/online and agnostic/realizable boosting.
