Innovations Autoencoder and its Application in One-class Anomalous Sequence Detection
This addresses a long-standing open problem in time series analysis for applications like anomaly detection, but appears incremental as it adapts deep learning to a known bottleneck.
The paper tackles the problem of extracting innovations sequences from non-Gaussian time series, which has been computationally challenging, by proposing a deep learning approach called Innovations Autoencoder (IAE) that uses a causal convolutional neural network, and applies it to one-class anomalous sequence detection with unknown models.
An innovations sequence of a time series is a sequence of independent and identically distributed random variables with which the original time series has a causal representation. The innovation at a time is statistically independent of the history of the time series. As such, it represents the new information contained at present but not in the past. Because of its simple probability structure, an innovations sequence is the most efficient signature of the original. Unlike the principle or independent component analysis representations, an innovations sequence preserves not only the complete statistical properties but also the temporal order of the original time series. An long-standing open problem is to find a computationally tractable way to extract an innovations sequence of non-Gaussian processes. This paper presents a deep learning approach, referred to as Innovations Autoencoder (IAE), that extracts innovations sequences using a causal convolutional neural network. An application of IAE to the one-class anomalous sequence detection problem with unknown anomaly and anomaly-free models is also presented.