Sparse Representation of Multivariate Extremes with Applications to Anomaly Ranking

03/31/2016
by   Nicolas Goix, et al.
0

Extremes play a special role in Anomaly Detection. Beyond inference and simulation purposes, probabilistic tools borrowed from Extreme Value Theory (EVT), such as the angular measure, can also be used to design novel statistical learning methods for Anomaly Detection/ranking. This paper proposes a new algorithm based on multivariate EVT to learn how to rank observations in a high dimensional space with respect to their degree of 'abnormality'. The procedure relies on an original dimension-reduction technique in the extreme domain that possibly produces a sparse representation of multivariate extremes and allows to gain insight into the dependence structure thereof, escaping the curse of dimensionality. The representation output by the unsupervised methodology we propose here can be combined with any Anomaly Detection technique tailored to non-extreme data. As it performs linearly with the dimension and almost linearly in the data (in O(dn log n)), it fits to large scale problems. The approach in this paper is novel in that EVT has never been used in its multivariate version in the field of Anomaly Detection. Illustrative experimental results provide strong empirical evidence of the relevance of our approach.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/13/2020

Informative Clusters for Multivariate Extremes

Capturing the dependence structure of multivariate extreme data is a maj...
research
09/26/2022

Real-time Anomaly Detection for Multivariate Data Streams

We present a real-time multivariate anomaly detection algorithm for data...
research
04/07/2021

Concentration bounds for the empirical angular measure with statistical learning applications

The angular measure on the unit sphere characterizes the first-order dep...
research
07/17/2019

A Multivariate Extreme Value Theory Approach to Anomaly Clustering and Visualization

In a wide variety of situations, anomalies in the behaviour of a complex...
research
04/12/2022

Unsupervised Anomaly and Change Detection with Multivariate Gaussianization

Anomaly detection is a field of intense research. Identifying low probab...
research
09/13/2019

LSTM-Based Anomaly Detection: Detection Rules from Extreme Value Theory

In this paper, we explore various statistical techniques for anomaly det...
research
02/05/2015

On Anomaly Ranking and Excess-Mass Curves

Learning how to rank multivariate unlabeled observations depending on th...

Please sign up or login with your details

Forgot password? Click here to reset