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 2106.11028cs.LG
收藏

在线预测任务的神经控制微分方程

Neural Controlled Differential Equations for Online Prediction Tasks

University of Oxford(牛津大学)

James Morrill, Patrick Kidger, Lingyi Yang, Terry Lyons

摘要:

神经控制微分方程(Neural CDE)是递归神经网络(RNN)的连续时间扩展,在不规则时间序列的建模函数方面实现了最先进的(SOTA)性能。为了在连续时间内解释离散数据,当前的实现依赖于数据的非因果插值。当整个时间序列被提前观察时,这是好的,但这意味着神经CDE不适合用于\textit{online prediction tasks},其中预测需要实时进行:递归网络的主要用例。在这里,我们展示了如何纠正这种限制。首先,我们确定了几个理论条件,插值计划的神经CDE应满足,如有界性和唯一性。其次,我们使用这些来激励新方案的引入,以解决这些问题,特别是提供可测量性(在线预测)和平滑性(速度)。第三,我们在MIMIC-IV医学数据库的三个连续监测任务上对我们的在线神经CDE模型进行了经验基准测试:我们在所有任务上对ODE基准测试的性能都有所提高,在三个任务中的两个任务上对SOTA非ODE基准测试的性能也有所提高。

英文摘要:

Neural controlled differential equations (Neural CDEs) are a continuous-time extension of recurrent neural networks (RNNs), achieving state-of-the-art (SOTA) performance at modelling functions of irregular time series. In order to interpret discrete data in continuous time, current implementations rely on non-causal interpolations of the data. This is fine when the whole time series is observed in advance, but means that Neural CDEs are not suitable for use in \textit{online prediction tasks}, where predictions need to be made in real-time: a major use case for recurrent networks. Here, we show how this limitation may be rectified. First, we identify several theoretical conditions that interpolation schemes for Neural CDEs should satisfy, such as boundedness and uniqueness. Second, we use these to motivate the introduction of new schemes that address these conditions, offering in particular measurability (for online prediction), and smoothness (for speed). Third, we empirically benchmark our online Neural CDE model on three continuous monitoring tasks from the MIMIC-IV medical database: we demonstrate improved performance on all tasks against ODE benchmarks, and on two of the three tasks against SOTA non-ODE benchmarks.

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。

↑