# Neural network-based CUSUM for online change-point detection

arXiv: https://arxiv.org/abs/2210.17312 · HTML: https://mlsanity.com/paper/2210.17312/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 45 references that are in the map.
- First posted on arXiv 31 Oct 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [On the Discrimination-Generalization Tradeoff in GANs](https://mlsanity.com/paper/1711.02771/) (2017)
- [Classification Logit Two-sample Testing by Neural Networks](https://mlsanity.com/paper/1909.11298/) (2019)
- [Neural Estimation of Statistical Divergences](https://mlsanity.com/paper/2110.03652/) (2021)
- [Training Neural Networks for Likelihood/Density Ratio Estimation](https://mlsanity.com/paper/1911.00405/) (2019)
- [Neural Tangent Kernel Maximum Mean Discrepancy](https://mlsanity.com/paper/2106.03227/) (2021)
- [Detecting change points in the large-scale structure of evolving networks](https://mlsanity.com/paper/1403.0989/) (2014)
- [Online Neural Networks for Change-Point Detection](https://mlsanity.com/paper/2010.01388/) (2020)
- [Change Point Detection in Correlation Networks](https://mlsanity.com/paper/1410.0761/) (2014)
- [Window-Limited CUSUM for Sequential Change Detection](https://mlsanity.com/paper/2206.06777/) (2022)
- [Memory-free Online Change-point Detection: A Novel Neural Network Approach](https://mlsanity.com/paper/2207.03932/) (2022)

## Built on by (most cited first, 5 of 5)

- [Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics](https://mlsanity.com/paper/2606.12476/) (2026)
- [WWAggr: A Window Wasserstein-based Aggregation for Ensemble Change Point Detection](https://mlsanity.com/paper/2506.08066/) (2025)
- [Resilience Characterization of AI-Native Wireless Receivers via Persistent Homology](https://mlsanity.com/paper/2605.22886/) (2026)
- [How Wrong Can a Good Predictor Be? Diverging Updates with Vanishing Predictive KL](https://mlsanity.com/paper/2609.11132/) (2026)
- [Learning to Detect Shifts in Unstructured Data Streams via Monitoring-by-Betting](https://mlsanity.com/paper/2610.17399/) (2026)

## Abstract (arXiv)

Change-point detection, detecting an abrupt change in the data distribution from sequential data, is a fundamental problem in statistics and machine learning. CUSUM is a popular statistical method for online change-point detection due to its efficiency from recursive computation and constant memory requirement, and it enjoys statistical optimality. CUSUM requires knowing the precise pre- and post-change distribution. However, post-change distribution is usually unknown a priori since it represents anomaly and novelty. Classic CUSUM can perform poorly when there is a model mismatch with actual data. While likelihood ratio-based methods encounter challenges facing high dimensional data, neural networks have become an emerging tool for change-point detection with computational efficiency and scalability. In this paper, we introduce a neural network CUSUM (NN-CUSUM) for online change-point detection. We also present a general theoretical condition when the trained neural networks can perform change-point detection and what losses can achieve our goal. We further extend our analysis by combining it with the Neural Tangent Kernel theory to establish learning guarantees for the standard performance metrics, including the average run length (ARL) and expected detection delay (EDD). The strong performance of NN-CUSUM is demonstrated in detecting change-point in high-dimensional data using both synthetic and real-world data.