Change Point Detection with Conceptors

TL;DR

This paper introduces a model-agnostic change point detection method using conceptor matrices and echo state networks, capable of handling nonlinear dependencies and providing consistent estimates with quantile inference.

Contribution

It proposes a novel, flexible approach for change point detection that works under arbitrary dependence structures without rigid model assumptions.

Findings

Consistent estimation of change points under mild conditions

Effective detection demonstrated on simulated data

Application to neural data shows practical utility

Abstract

Offline change point detection retrospectively locates change points in a time series. Many nonparametric methods that target i.i.d. mean and variance changes fail in the presence of nonlinear temporal dependence, and model based methods require a known, rigid structure. For the at most one change point problem, we propose use of a conceptor matrix to learn the characteristic dynamics of a baseline training window with arbitrary dependence structure. The associated echo state network acts as a featurizer of the data, and change points are identified from the nature of the interactions between the features and their relationship to the baseline state. This model agnostic method can suggest potential locations of interest that warrant further study. We prove that, under mild assumptions, the method provides a consistent estimate of the true change point, and quantile estimates are produced via a moving block bootstrap of the original data. The method is evaluated with clustering metrics and Type 1 error control on simulated data, and applied to publicly available neural data from rats experiencing bouts of non-REM sleep prior to exploration of a radial maze. With sufficient spacing, the framework provides a simple extension to the sparse, multiple change point problem.