Machine-learned predictors, although achieving very good results for inputs resembling training data, cannot possibly provide perfect predictions in all situations. Still, decision-making systems that are based on such predictors need not only benefit from good predictions, but should also achieve a decent performance when the predictions are inadequate. In this paper, we propose a prediction setup for arbitrary metrical task systems (MTS) (e.g., caching, k-server and convex body chasing) and online matching on the line. We utilize results from the theory of online algorithms to show how to make the setup robust. Specifically for caching, we present an algorithm whose performance, as a function of the prediction error, is exponentially better than what is achievable for general MTS. Finally, we present an empirical evaluation of our methods on real world datasets, which suggests practicality.

机器学习的预测器，虽然对类似于训练数据的输入取得了非常好的结果，但不可能在所有情况下都提供完美的预测。尽管如此，基于此类预测器的决策系统不仅需要从良好的预测中获益，而且还应该在预测不充分时取得不错的性能。在本文中，我们提出了一种用于任意度量任务系统 (MTS) （例如， 缓存、k-服务器和凸体追逐）和线上在线匹配的预测设置. 我们利用在线算法理论的结果来展示如何使设置稳健。特别是对于缓存，我们提出了一种算法，其性能作为预测误差的函数，比一般 MTS 的性能要好得多。最后，我们在现实世界的数据集上对我们的方法进行了实证评估，这表明了实用性。