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 1911.12436cs.LGstat.ML
收藏

AR-Net:一个简单的时间序列自回归神经网络

AR-Net: A simple Auto-Regressive Neural Network for time-series

Stanford University(斯坦福大学);Facebook, Inc.(脸书公司)

Oskar Triebe, Nikolay Laptev, Ram Rajagopal

摘要:

在本文中,我们提出了一个新的框架,结合了最好的传统的统计模型和神经网络的时间序列建模。我们专注于具有长期依赖性的时间序列,这是监控细粒度数据(例如,分钟,秒,毫秒)所需的,在操作用例中很普遍。传统的模型,如自回归拟合最小二乘(经典AR)可以建模的时间序列与一个简洁和可解释的模型。在处理长期依赖关系时,经典AR模型在适应大数据时可能会变得非常缓慢。最近,序列到序列模型,如递归神经网络,最初用于自然语言处理,已成为流行的时间序列。然而,对于典型的时间序列数据来说,它们可能过于复杂,缺乏可解释性。需要一个可扩展和可解释的模型来桥接基于统计和深度学习的方法。作为实现这一目标的第一步,我们提出了建模AR过程动态使用前馈神经网络的方法,称为AR网络。我们表明,AR-Net与Classic-AR一样可解释,但也可扩展到长期依赖关系。我们的研究结果导致三个主要结论:首先,AR-Net学习与Classic-AR相同的AR系数,因此同样可解释。其次,相对于AR过程的阶数的计算复杂性对于AR-Net是线性的,而对于Classic-AR是二次的。这使得在细粒度数据中建模长期依赖性成为可能。第三,通过引入正则化,AR-Net自动选择和学习稀疏AR系数。这消除了需要知道AR过程的确切顺序,并允许学习具有长程依赖关系的模型的稀疏权重。

英文摘要:

In this paper we present a new framework for time-series modeling that combines the best of traditional statistical models and neural networks. We focus on time-series with long-range dependencies, needed for monitoring fine granularity data (e.g. minutes, seconds, milliseconds), prevalent in operational use-cases. Traditional models, such as auto-regression fitted with least squares (Classic-AR) can model time-series with a concise and interpretable model. When dealing with long-range dependencies, Classic-AR models can become intractably slow to fit for large data. Recently, sequence-to-sequence models, such as Recurrent Neural Networks, which were originally intended for natural language processing, have become popular for time-series. However, they can be overly complex for typical time-series data and lack interpretability. A scalable and interpretable model is needed to bridge the statistical and deep learning-based approaches. As a first step towards this goal, we propose modelling AR-process dynamics using a feed-forward neural network approach, termed AR-Net. We show that AR-Net is as interpretable as Classic-AR but also scales to long-range dependencies. Our results lead to three major conclusions: First, AR-Net learns identical AR-coefficients as Classic-AR, thus being equally interpretable. Second, the computational complexity with respect to the order of the AR process, is linear for AR-Net as compared to a quadratic for Classic-AR. This makes it possible to model long-range dependencies within fine granularity data. Third, by introducing regularization, AR-Net automatically selects and learns sparse AR-coefficients. This eliminates the need to know the exact order of the AR-process and allows to learn sparse weights for a model with long-range dependencies.

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。

↑