arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1106.0730stat.MLcs.LG
收藏

平稳序列的拉德马赫复杂度

Rademacher complexity of stationary sequences

Indiana University(印第安纳大学);Carnegie Mellon University(卡内基梅隆大学)

Daniel J. McDonald, Cosma Rohilla Shalizi

摘要:

我们展示了如何控制时间序列模型的泛化误差,其中过去的结果值被用来预测未来的值。结果是基于标准i.i.d.的推广。集中不等式的依赖数据没有混合假设常见的时间序列设置。我们的证明和结果是简单的,比以前的分析依赖的数据或随机对手,使用顺序Rademacher复杂度,而不是预期的拉德马赫复杂度的i.i.d.流程.我们还得出经验Rademacher的结果,没有混合的假设,从而在完全可计算的上限。

英文摘要:

We show how to control the generalization error of time series models wherein past values of the outcome are used to predict future values. The results are based on a generalization of standard i.i.d. concentration inequalities to dependent data without the mixing assumptions common in the time series setting. Our proof and the result are simpler than previous analyses with dependent data or stochastic adversaries which use sequential Rademacher complexities rather than the expected Rademacher complexity for i.i.d. processes. We also derive empirical Rademacher results without mixing assumptions resulting in fully calculable upper bounds.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑