online gradient descent:
Theorem:
For any closed convex action set A such that ,
for any subdifferentiable loss with bounded subgradient , the OGD strategy with parameters
and
satisfies:
strongly convex loss with bounded subgradient
online gradient descent:
Theorem:
For any closed convex action set A such that ,
for any subdifferentiable loss with bounded subgradient , the OGD strategy with parameters
and
satisfies:
strongly convex loss with bounded subgradient
牛客博客，记录你的成长
京公网安备 11010502036488号