2012
NeurIPS
NeurIPS 2012
Locating Changes in Highly Dependent Data with Unknown Number of Change Points
Abstract
The problem of multiple change point estimation is considered for sequences with unknown number of change points. A consistency framework is suggested that is suitable for highly dependent time-series, and an asymptotically consistent algorithm is proposed. In order for the consistency to be established the only assumption required is that the data is generated by stationary ergodic time-series distributions. No modeling, independence or parametric assumptions are made; the data are allowed to be dependent and the dependence can be of arbitrary form. The theoretical results are complemented with experimental evaluations.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Data Science & Analytics and Mathematics & Optimization
📈
Trend Setter
- Anomaly Detection
🐣
Hot Topic Early Bird
- time series
Authors
Topics
Machine Learning > Core Methods > Clustering
Machine Learning > Learning Types > Unsupervised Learning
Machine Learning > Optimization & Theory > Statistical Learning
Data Science & Analytics > Methods > Time Series Analysis
Mathematics & Optimization > Statistics
Machine Learning > Optimization & Theory > Statistics
Artificial Intelligence > Core AI > Anomaly Detection
Keywords
change point detection
time series analysis
statistical learning
statistical consistency
time series
nonparametric estimation
ergodic processes
change point estimation
highly dependent time series
stationary ergodic
multiple change points
asymptotic consistency
stationary ergodic process
ergodic process
dependent data