Fundamental limits of distributed multiclass classification from simple binary decisions

By Ioannis Papageorgiou · Paper · stat.ML

We consider the problem of constructing a $K$-class classifier from the combination of $O(\log K)$ simple binary classifiers -- this is a natural paradigm to construct a sophisticated classifier in a distributed manner with each agent performing a relatively straightforward task.

Stat.ml

View original

HomeResourceLoading…