When lookout sees crackle: Anomaly detection via kernel density estimation

TL;DR

This paper introduces an improved anomaly detection algorithm called lookout, utilizing kernel density estimates with theoretical guarantees, demonstrating enhanced performance and robustness over previous versions across various examples.

Contribution

The paper presents an updated lookout algorithm with a consistent kernel density estimator and multivariate scaling, backed by theoretical guarantees and improved empirical performance.

Findings

The updated lookout algorithm is consistent.

Multivariate scaling enhances robustness and efficiency.

The new method outperforms previous versions on diverse datasets.

Abstract

We present an updated version of lookout -- an algorithm for detecting anomalies using kernel density estimates with bandwidth based on Rips death diameters -- with theoretical guarantees. The kernel density estimator for updated lookout is shown to be consistent, and the proposed multivariate scaling is robust and efficient. We show our updated algorithm performs better than the previous version on diverse examples.