MLLGOct 21, 2016

Maximally Divergent Intervals for Anomaly Detection

arXiv:1610.06761v16 citations
Originality Incremental advance
AI Analysis

This addresses anomaly detection for multivariate time series data, presenting an incremental improvement over existing methods.

The paper tackles batch anomaly detection in multivariate time series by maximizing Kullback-Leibler divergence between data distributions inside and outside intervals, showing benefits over methods that treat time steps independently without interval optimization.

We present new methods for batch anomaly detection in multivariate time series. Our methods are based on maximizing the Kullback-Leibler divergence between the data distribution within and outside an interval of the time series. An empirical analysis shows the benefits of our algorithms compared to methods that treat each time step independently from each other without optimizing with respect to all possible intervals.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes