...
首页> 外文期刊>Information Theory, IEEE Transactions on >PAC-Bayesian Inequalities for Martingales
【24h】

PAC-Bayesian Inequalities for Martingales

机译:马丁格尔斯的PAC-贝叶斯不等式

获取原文
获取原文并翻译 | 示例
           

摘要

We present a set of high-probability inequalities that control the concentration of weighted averages of multiple (possibly uncountably many) simultaneously evolving and interdependent martingales. Our results extend the PAC-Bayesian (probably approximately correct) analysis in learning theory from the i.i.d. setting to martingales opening the way for its application to importance weighted sampling, reinforcement learning, and other interactive learning domains, as well as many other domains in probability theory and statistics, where martingales are encountered. We also present a comparison inequality that bounds the expectation of a convex function of a martingale difference sequence shifted to the $[0, 1]$ interval by the expectation of the same function of independent Bernoulli random variables. This inequality is applied to derive a tighter analog of Hoeffding–Azuma's inequality.
机译:我们提出了一组高概率不等式,这些不等式控制着同时演化和相互依存的mar的多重(可能无数)的加权平均值的集中。我们的结果扩展了i.i.d在学习理论中的PAC-贝叶斯分析(可能近似正确)。设置了mar,这为在重要性加权采样,强化学习和其他交互式学习领域以及概率论和统计学中遇到other的许多其他领域中的应用打开了道路。我们还提出了一个比较不等式,该比较不等式通过独立伯努利随机变量的相同函数的期望来限制a差序列的凸函数向$ [0,1] $区间的期望。应用该不等式可以得出霍夫丁-阿祖玛不等式的更紧密的近似。

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