The Impossibility of Parallelizing Boosting

01/23/2023

∙

by   Amin Karbasi, et al.

∙

0

∙

share

The aim of boosting is to convert a sequence of weak learners into a strong learner. At their heart, these methods are fully sequential. In this paper, we investigate the possibility of parallelizing boosting. Our main contribution is a strong negative result, implying that significant parallelization of boosting requires an exponential blow-up in the total computing resources needed for training.