论文标题
单纯上的零订单优化的注释
A Note on Zeroth-Order Optimization on the Simplex
论文作者
论文摘要
我们为概率单纯性定义的平滑函数构建一个零阶梯度估计器。提出的估计器仅查询单纯形。我们证明,当使用此估算器而不是精确的梯度运行时,投影梯度下降和指数权重算法时,以$ \ Mathcal O(T^{ - 1/4})$ rate收敛。
We construct a zeroth-order gradient estimator for a smooth function defined on the probability simplex. The proposed estimator queries the simplex only. We prove that projected gradient descent and the exponential weights algorithm, when run with this estimator instead of exact gradients, converge at a $\mathcal O(T^{-1/4})$ rate.