Algorithms with Predictions

06/16/2020

∙

by   Michael Mitzenmacher, et al.

∙

Google

∙

Harvard University

∙

0

∙

share

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.