This paper addresses the problem of online learning in metric spaces using exponential weights. We extend the analysis of the exponentially weighted average forecaster, traditionally studied in a Euclidean settings, to a more abstract framework. Our results rely on the notion of barycenters, a suitable version of Jensen's inequality and a synthetic notion of lower curvature bound in metric spaces known as the measure contraction property. We also adapt the online-to-batch conversion principle to apply our results to a statistical learning framework.
翻译:本文用指数权重处理计量空间的在线学习问题。 我们对传统上在欧几里德环境下研究的指数加权平均预报器的分析扩大到一个更抽象的框架。 我们的结果依赖于巴里中心的概念、詹森不平等的合适版本和在被称为测量缩缩缩属性的计量空间内捆绑的低曲线的合成概念。 我们还调整了在线到批量转换原则,将我们的结果应用于统计学习框架。