Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging
Amélie Héliou 1 Matthieu Martin 1 Panayotis Mertikopoulos 2 1 Thibaud Rahier 1
Abstract also requires that the problem’s objective remain stationary
during the query process.
We propose a hierarchical version of dual averag-
ing for zeroth-order online non-convex optimiza- Motivated by applications to online ad auctions and recom-
tion – i.e., ...


雷达卡




京公网安备 11010802022788号







