# Online Neural Networks for Change-Point Detection

arXiv: https://arxiv.org/abs/2010.01388 · HTML: https://mlsanity.com/paper/2010.01388/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2020.

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

- [Neural network-based CUSUM for online change-point detection](https://mlsanity.com/paper/2210.17312/) (2022)
- [InDiD: Instant Disorder Detection via Representation Learning](https://mlsanity.com/paper/2106.02602/) (2021)
- [Unsupervised Text Segmentation via Kernel Change-Point Detection on Sentence Embeddings](https://mlsanity.com/paper/2601.18788/) (2026)
- [Online detection of failures generated by storage simulator](https://mlsanity.com/paper/2101.07100/) (2021)
- [Usage of specific attention improves change point detection](https://mlsanity.com/paper/2204.08175/) (2022)
- [Consistent Kernel Change-Point Detection under m-Dependence for Text Segmentation](https://mlsanity.com/paper/2510.03437/) (2025)
- [BayesSeg: A Bayesian Optimization Framework for State Segmentation of Electricity Consumption Time Series](https://mlsanity.com/paper/2608.00513/) (2026)
- [High-Dimensional Online Change Point Detection with Adaptive Thresholding and Interpretability](https://mlsanity.com/paper/2609.24278/) (2026)

## Abstract (arXiv)

Moments when a time series changes its behavior are called change points. Occurrence of change point implies that the state of the system is altered and its timely detection might help to prevent unwanted consequences. In this paper, we present two change-point detection approaches based on neural networks and online learning. These algorithms demonstrate linear computational complexity and are suitable for change-point detection in large time series. We compare them with the best known algorithms on various synthetic and real world data sets. Experiments show that the proposed methods outperform known approaches. We also prove the convergence of the algorithms to the optimal solutions and describe conditions rendering current approach more powerful than offline one.