一种时间序列图建模的高效方法
An Efficient Approach to Graphical Modelling of Time Series
AI总结：
针对Matsuda提出的高维平稳高斯时间序列图模型后向选择算法计算成本过高的问题，本研究通过多重假设检验重构方法，将计算复杂度降低$O(p^2)$，检验功效不逊原方法且易并行加速。
摘要：
Matsuda 最近提出了一种为 $p$ 维向量平稳高斯时间序列选择图模型的方法，该方法使用 Kullback-Leibler 散度度量来定义检验统计量。该统计量被用于后向选择过程，但该算法在 $p$ 较大时计算成本高得令人望而却步，且未假设模型具有高度稀疏性。我们证明，通过多重假设检验进行重构可将计算时间降低 $O(p^2)$ 量级；仿真结果也证实，新方法的检验功效至少与 Matsuda 那套慢得多的方法相当。此外，新方案可轻松实现并行化，从而进一步提升速度。
英文摘要：
A method for selecting a graphical model for $p$-vector-valued stationary Gaussian time series was recently proposed by Matsuda and uses the Kullback-Leibler divergence measure to define a test statistic. This statistic was used in a backward selection procedure, but the algorithm is prohibitively expensive for large $p.$ A high degree of sparsity is not assumed. We show that reformulation in terms of a multiple hypothesis test reduces computation time by $O(p^2)$ and simulations support the assertion that power levels are attained at least as good as those achieved by Matsuda's much slower approach. Moreover, the new scheme is readily parallelizable for even greater speed gains.
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。
