论文标题
具有预测的算法
Algorithms with Predictions
论文作者
论文摘要
我们介绍了使用将机器学习的预测应用于输入的算法,以规避最坏情况分析。我们的目标是在这些预测良好时具有接近最佳性能的算法,但是当预测有较大错误时,恢复了无预测的最坏情况。
We introduce algorithms that use predictions from machine learning applied to the input to circumvent worst-case analysis. We aim for algorithms that have near optimal performance when these predictions are good, but recover the prediction-less worst case behavior when the predictions have large errors.