# AER: Auto-Encoder with Regression for Time Series Anomaly Detection

arXiv: https://arxiv.org/abs/2212.13558 · HTML: https://mlsanity.com/paper/2212.13558/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 27 Dec 2022.

## Builds on (most cited first, 11 of 11)

- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder](https://mlsanity.com/paper/1711.00614/) (2017)
- [MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks](https://mlsanity.com/paper/1901.04997/) (2019)
- [Multivariate Time-series Anomaly Detection via Graph Attention Network](https://mlsanity.com/paper/2009.02040/) (2020)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis](https://mlsanity.com/paper/1807.07814/) (2018)
- [TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks](https://mlsanity.com/paper/2009.07769/) (2020)
- [Sintel: A Machine Learning Framework to Extract Insights from Signals](https://mlsanity.com/paper/2204.09108/) (2022)
- [VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models](https://mlsanity.com/paper/2108.02550/) (2021)

## Built on by (most cited first, 8 of 8)

- [Large language models can be zero-shot anomaly detectors for time series?](https://mlsanity.com/paper/2405.14755/) (2024)
- [Harnessing Vision-Language Models for Time Series Anomaly Detection](https://mlsanity.com/paper/2506.06836/) (2025)
- [Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancy](https://mlsanity.com/paper/2509.21190/) (2025)
- [M2AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding](https://mlsanity.com/paper/2504.15225/) (2025)
- [Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows](https://mlsanity.com/paper/2404.17381/) (2024)
- [Generative Pre-Training of Time-Series Data for Unsupervised Fault Detection in Semiconductor Manufacturing](https://mlsanity.com/paper/2309.11427/) (2023)
- [OrionBench: Benchmarking Time Series Generative Models in the Service of the End-User](https://mlsanity.com/paper/2310.17748/) (2023)
- [Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities](https://mlsanity.com/paper/2511.14945/) (2025)

## Abstract (arXiv)

Anomaly detection on time series data is increasingly common across various industrial domains that monitor metrics in order to prevent potential accidents and economic losses. However, a scarcity of labeled data and ambiguous definitions of anomalies can complicate these efforts. Recent unsupervised machine learning methods have made remarkable progress in tackling this problem using either single-timestamp predictions or time series reconstructions. While traditionally considered separately, these methods are not mutually exclusive and can offer complementary perspectives on anomaly detection. This paper first highlights the successes and limitations of prediction-based and reconstruction-based methods with visualized time series signals and anomaly scores. We then propose AER (Auto-encoder with Regression), a joint model that combines a vanilla auto-encoder and an LSTM regressor to incorporate the successes and address the limitations of each method. Our model can produce bi-directional predictions while simultaneously reconstructing the original time series by optimizing a joint objective function. Furthermore, we propose several ways of combining the prediction and reconstruction errors through a series of ablation studies. Finally, we compare the performance of the AER architecture against two prediction-based methods and three reconstruction-based methods on 12 well-known univariate time series datasets from NASA, Yahoo, Numenta, and UCR. The results show that AER has the highest averaged F1 score across all datasets (a 23.5% improvement compared to ARIMA) while retaining a runtime similar to its vanilla auto-encoder and regressor components. Our model is available in Orion, an open-source benchmarking tool for time series anomaly detection.