arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.05259cs.LGstat.ML
收藏

随机Warping序列:一种时间序列嵌入的随机特征方法

Random Warping Series: A Random Features Method for Time-Series Embedding

IBM Research(IBM研究院);Carnegie Mellon University(卡内基梅隆大学);College of William and Mary(威廉与玛丽学院);University of Texas at Austin(得克萨斯大学奥斯汀分校)

Lingfei Wu, Ian En-Hsu Yen, Jinfeng Yi, Fangli Xu, Qi Lei, Michael Witbrock

摘要:

几十年来,时间序列数据分析一直是人们感兴趣的问题,而动态时间弯曲(DTW)一直是最广泛采用的技术来衡量时间序列之间的差异。此后,在DTW的精神下,提出了许多全局对齐内核,以将其使用扩展到基于内核的估计方法,例如支持向量机。然而,这些内核遭受对角优势的革兰氏矩阵和二次复杂性w.r.t.样本量。在这项工作中,我们研究了一个家庭的感知正定(p. d.)核,其特征嵌入由\emph{Random Warping Series (RWS)}的分布给出。所提出的核不受对角优势的问题,而自然享有\emph{Random Features}(RF)的近似,这降低了现有的基于DTW的技术的计算复杂性从二次到线性的时间序列的数量和长度。我们还研究了无界长度时间序列域的RF逼近的收敛性。我们在16个基准数据集上进行的大量实验表明,RWS在准确性和计算时间方面优于或匹配最先进的分类和聚类方法。我们的代码和数据可在{ \url{https://github.com/IBM/RandomWarpingSeries} }获得。

英文摘要:

Time series data analytics has been a problem of substantial interests for decades, and Dynamic Time Warping (DTW) has been the most widely adopted technique to measure dissimilarity between time series. A number of global-alignment kernels have since been proposed in the spirit of DTW to extend its use to kernel-based estimation method such as support vector machine. However, those kernels suffer from diagonal dominance of the Gram matrix and a quadratic complexity w.r.t. the sample size. In this work, we study a family of alignment-aware positive definite (p.d.) kernels, with its feature embedding given by a distribution of \emph{Random Warping Series (RWS)}. The proposed kernel does not suffer from the issue of diagonal dominance while naturally enjoys a \emph{Random Features} (RF) approximation, which reduces the computational complexity of existing DTW-based techniques from quadratic to linear in terms of both the number and the length of time-series. We also study the convergence of the RF approximation for the domain of time series of unbounded length. Our extensive experiments on 16 benchmark datasets demonstrate that RWS outperforms or matches state-of-the-art classification and clustering methods in both accuracy and computational time. Our code and data is available at { \url{https://github.com/IBM/RandomWarpingSeries}}.

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。

↑