Online Learning with an Almost Perfect Expert

Proc. Natl. Acad. Sci. U.S.A., Volume abs/1807.11169, 2019.

Cited by: 0|Bibtex|Views17
EI WOS
Other Links: dblp.uni-trier.de|pubmed.ncbi.nlm.nih.gov|academic.microsoft.com|arxiv.org

Abstract:

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

Code:

Data:

Your rating :
0

 

Tags
Comments