A Fast and Efficient Change-Point Detection Framework Based on Approximate $k$-Nearest Neighbor Graphs

  title={A Fast and Efficient Change-Point Detection Framework Based on Approximate \$k\$-Nearest Neighbor Graphs},
  author={Yi-Wei Liu and Hao Chen},
  journal={IEEE Transactions on Signal Processing},
  • Yi-Wei Liu, Hao Chen
  • Published 24 June 2020
  • Computer Science
  • IEEE Transactions on Signal Processing
Change-point analysis is thriving in this Big Data era to address problems arising in many fields where massive data sequences are collected to study complicated phenomena over time. It plays an important role in processing these data by segmenting a long sequence into homogeneous parts for follow-up studies. The task requires the method to be able to process large datasets quickly and deal with various types of changes for high-dimensional data. We propose a new approach making use of… 

Figures and Tables from this paper

AutoSW: a new automated sliding window-based change point detection method for sensor data

A new change point detection method, AutoSW, is presented, where the window width is automatically calculated, based on a Sliding Window search method of the Python ruptures package and uses a subset of statistical concepts to compute a possibly optimal window width.

RISE: Rank in Similarity Graph Edge-Count Two-Sample Test

A new non-parametric two-sample testing procedure, RISE, constructed on a rank-weighted similarity graph, such as the k -nearest neighbor graph, which exhibits good power under a wide range of alternatives compared to existing methods, as shown in extensive simulations.



Asymptotic distribution-free change-point detection for multivariate and non-Euclidean data

We consider the testing and estimation of change-points, locations where the distribution abruptly changes, in a sequence of multivariate or non-Euclidean observations. We study a nonparametric

The Grand Budapest Hotel: an fMRI dataset in response to a socially-rich, naturalistic movie

This dataset provides researchers with fMRI data that can be used to explore social cognitive processes and face processing, adding to the existing neuroimaging datasets that sample brain activity with naturalistic movies.

Seeded Binary Segmentation: A general methodology for fast and optimal change point detection

This work shows that seeded binary segmentation leads to a near-linear time approach (i.e. linear up to a logarithmic factor) independent of the underlying number of change points, and demonstrates the methodology for high-dimensional settings with an inverse covariance change point detection problem.

Revisiting kd-tree for Nearest Neighbor Search

Empirically validate the search accuracy and the query time guarantees of the proposed schemes, demonstrating the significantly improved scaling for same level of accuracy.

Change-Point Detection for Graphical Models in the Presence of Missing Values

This work proposes three imputation like methods for change points in high-dimensional covariance structures with an emphasis on challenging scenarios with missing values and investigates their implications on common losses used for change point detection.

A Universal Nonparametric Event Detection Framework for Neuropixels Data

It is hypothesized that neural activities underlying spontaneous behavior, though distributed brainwide, show evidences for network modularity, and the proposed framework to be a useful off-the-shelf analysis tool to the neuroscience community as new electrophysiological recording techniques continue to drive an explosive proliferation in the number and size of data sets.

Spontaneous behaviors drive multidimensional, brainwide activity

It is found that ongoing activity in visual cortex is high dimensional: More than a hundred latent dimensions could be reliably extracted from the population activity, suggesting information encoded nearly anywhere in the forebrain is combined with behavioral state variables into a mixed representation.

Applications of Nonparametric Change-Point Detection Methods

The nonparametric methods of change-point detection developed in this book have been tested many times by statistical simulation. However, the most interesting point, in our opinion, is running the

Scan B-statistic for kernel change-point detection

This article proposes a computationally efficient kernel-based statistics for change-point detection inspired by the recently developed B-statistics and characterization of the tail probability of these statistics using the change-of-measure technique, which focuses on characterizing the tail of the detection statistics rather than obtaining its asymptotic distribution under the null distribution.