Concentration bounds for two time scale stochastic approximation
Concentration bounds for two time scale stochastic approximation
复制标题
两个时间尺度随机近似的浓度界限
DOI：
10.1109/allerton.2018.8636078
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
S. Pattathil
中科院分区：
文献类型：
--
作者：
V. Borkar;S. Pattathil
将两个时间尺度的随机逼近方案看作是奇摄动微分方程的噪声离散化，我们获得了其迭代的浓度界，该迭代以可量化的高概率捕获其行为。
Viewing a two time scale stochastic approximation scheme as a noisy discretization of a singularly perturbed differential equation, we obtain a concentration bound for its iterates that captures its behavior with quantifiable high probability.