arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.08781cs.LG
收藏

LORD:对数签名在神经粗糙微分方程中的低维嵌入

LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations

Yonsei University(延世大学)

Jaehoon Lee, Jinsung Jeon, Sheo yon Jhin, Jihyeon Hyeong, Jayoung Kim, Minju Jo, Kook Seungji, Noseong Park

摘要:

处理非常长的时间序列数据的问题(例如,长度超过10,000)是机器学习中的一个长期存在的研究问题。最近,一个突破,称为神经粗糙微分方程(NRDE),已被提出,并已表明它能够处理这样的数据。他们的主要概念是使用对数签名变换,这是已知的是更有效的不规则的长时间序列的傅立叶变换,转换成一个非常长的时间序列样本相对较短的一系列特征向量。然而,对数签名变换导致非平凡的空间开销。为此,我们提出了低维嵌入的日志签名(LORD)的方法,我们定义了一个基于NRDE的自动编码器植入更高的深度日志签名的知识到较低的深度日志签名。我们表明,编码器成功地结合了更高深度和更低深度的日志签名知识,这大大稳定了训练过程,提高了模型的准确性。在对基准数据集的实验中,我们的方法在各种分类和预测评价指标方面的改进率高达75%.

英文摘要:

The problem of processing very long time-series data (e.g., a length of more than 10,000) is a long-standing research problem in machine learning. Recently, one breakthrough, called neural rough differential equations (NRDEs), has been proposed and has shown that it is able to process such data. Their main concept is to use the log-signature transform, which is known to be more efficient than the Fourier transform for irregular long time-series, to convert a very long time-series sample into a relatively shorter series of feature vectors. However, the log-signature transform causes non-trivial spatial overheads. To this end, we present the method of LOweR-Dimensional embedding of log-signature (LORD), where we define an NRDE-based autoencoder to implant the higher-depth log-signature knowledge into the lower-depth log-signature. We show that the encoder successfully combines the higher-depth and the lower-depth log-signature knowledge, which greatly stabilizes the training process and increases the model accuracy. In our experiments with benchmark datasets, the improvement ratio by our method is up to 75\% in terms of various classification and forecasting evaluation metrics.

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。

↑