arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.13625cs.ITcond-mat.dis-nnmath.ITmath.STstat.TH
收藏

高维时间序列的信息论极限与近似消息传递

Information-theoretic limits and approximate message-passing for high-dimensional time series

Daria Tieplova, Samriddha Lahiry, Jean Barbier

AI总结:

针对高维时间序列非稀疏场景下现有分析受限的问题,本文推导了无稀疏假设、特征与采样点成比例增长的随机回归模型的归一化互信息及最小均方误差单字母公式,并实证验证VAMP算法推断性能稳健且常达统计最优。

摘要:

高维时间序列出现在诸多科研场景中,需要采用精细的方法来建模和分析其潜在的依赖结构。目前的理论进展往往依赖于对潜在信号稀疏性的严格假设。在非稀疏情形下,相关分析主要集中于设计矩阵具有独立行的线性回归模型。本文拓展了研究范围,探究了特征数量与采样点数量成比例增长、且不对信号做稀疏性假设的高维时间序列模型。具体而言,我们考虑随机回归模型,推导了观测值与信号之间归一化互信息的单字母公式,以及最小均方误差的单字母公式。我们还通过实证研究了向量近似消息传递(vector approximate message passing,VAMP)算法,结果表明,尽管缺乏理论保证,该算法在我们的时间序列模型中用于推断的性能十分稳健,且通常达到统计最优。

英文摘要:

High-dimensional time series appear in many scientific setups, demanding a nuanced approach to model and analyze the underlying dependence structure. Theoretical advancements so far often rely on stringent assumptions regarding the sparsity of the underlying signal. In non-sparse regimes, analyses have primarily focused on linear regression models with the design matrix having independent rows. In this paper, we expand the scope by investigating a high-dimensional time series model wherein the number of features grows proportionally to the number of sampling points, without assuming sparsity in the signal. Specifically, we consider the stochastic regression model and derive a single-letter formula for the normalized mutual information between observations and the signal, as well as for minimum mean-square errors. We also empirically study the vector approximate message passing VAMP algorithm and show that, despite the lack of theoretical guarantees, its performance for inference in our time series model is robust and often statistically optimal.

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。

↑