Online Learning with an Almost Perfect Expert
Proc. Natl. Acad. Sci. U.S.A., Volume abs/1807.11169, 2019.
We study multiclass online learning, where a forecaster predicts a sequence of elements drawn from a finite set using the advice of n experts. Our main contributions are to analyze the scenario where the best expert makes a bounded number b of mistakes and to show that, in the low-error regime where [Formula: see text], the expected numbe...More
Full Text (Upload PDF)
PPT (Upload PPT)