...
首页> 外文期刊>IEEE Transactions on Automatic Control >An alternative proof for convergence of stochastic approximationalgorithms
【24h】

An alternative proof for convergence of stochastic approximationalgorithms

机译:随机近似算法收敛的另一种证明

获取原文
获取原文并翻译 | 示例
           

摘要

An alternative proof for convergence of stochastic approximation algorithms is provided. The proof is completely deterministic, very elementary (involving only basic notions of convergence), and direct in that it remains in a discrete setting. An alternative form of the Kushner-Clark condition is introduced and utilized and the results are the first to prove necessity for general gain sequences in a Hilbert space setting
机译:提供了随机逼近算法收敛的另一种证明。该证明是完全确定性的,非常基础的(仅涉及收敛的基本概念),并且直接因为它保持在离散的环境中。引入并利用了Kushner-Clark条件的另一种形式,该结果首次证明了希尔伯特空间设置中一般增益序列的必要性

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号