发帖
雷达卡
Boosting for Online Convex Optimization
Elad Hazan 1 2 Karan Singh 3
Abstract et al., 2012). Itp is well established that the regret can be
bounded by O( T log |H|), where |H| is the number of
We consider the decision-making framework of
experts, and that this is tight. However, in many problems
online convex optimization with a very large num-
...
京公网安备 11010802022788号
