首页> 外文期刊>IFAC PapersOnLine >Robust Sparse Approximations for Stochastic Dynamical Systems
【24h】

Robust Sparse Approximations for Stochastic Dynamical Systems

机译:随机动力系统的鲁棒稀疏近似

获取原文
           

摘要

Inferring the exact topology of the interactions in a large, stochastic dynamical system from time-series data can often be prohibitive computationally and statistically without strong side information. One alternative is to seek approximations of the system topology that nonetheless describe the data well. In recent works, algorithms were proposed to identify sparse approximations which are optimal in terms of Kullback-Leibler divergence. Those algorithms relied on point estimates of statistics from the data. In this work, we investigate the more practical setting where point estimates are not reliable. We propose an algorithm to identify sparse, connected approximations that are robust to estimation error.
机译:从时序数据推断大型随机动力学系统中相互作用的确切拓扑通常在没有强大辅助信息的情况下在计算和统计上都是令人望而却步的。一种替代方法是寻求仍然能很好描述数据的系统拓扑的近似值。在最近的工作中,提出了用于识别稀疏近似的算法,该稀疏近似在Kullback-Leibler发散方面是最佳的。这些算法依赖于数据的统计点估计。在这项工作中,我们研究了点估计不可靠的更实际的设置。我们提出了一种算法,该算法可识别对估计误差具有鲁棒性的稀疏连通近似。

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