Non-Exponentially Weighted Aggregation:
Regret Bounds for Unbounded Loss Functions
Pierre Alquier 1
Abstract the sub-gradient
√ of `t can be used. Such strategies lead to
regret in T under the additional assumption that the `t are
We tackle the problem of online optimization with
Lipschitz. The regre ...


雷达卡




京公网安备 11010802022788号







