# --------------------------------------------
# CITATION file created with {cffr} R package
# See also: https://docs.ropensci.org/cffr/
# --------------------------------------------
 
cff-version: 1.2.0
message: 'To cite package "fastcpd" in publications use:'
type: software
license: GPL-3.0-or-later
title: 'fastcpd: Fast Change Point Detection via Sequential Gradient Descent'
version: 0.14.5
doi: 10.48550/arXiv.2404.05933
identifiers:
- type: doi
  value: 10.32614/CRAN.package.fastcpd
abstract: Implements fast change point detection algorithm based on the paper "Sequential
  Gradient Descent and Quasi-Newton's Method for Change-Point Analysis" by Xianyang
  Zhang, Trisha Dawn <https://proceedings.mlr.press/v206/zhang23b.html>. The algorithm
  is based on dynamic programming with pruning and sequential gradient descent. It
  is able to detect change points a magnitude faster than the vanilla Pruned Exact
  Linear Time(PELT). The package includes examples of linear regression, logistic
  regression, Poisson regression, penalized linear regression data, and whole lot
  more examples with custom cost function in case the user wants to use their own
  cost function.
authors:
- family-names: Li
  given-names: Xingchi
  email: anthony.li@stat.tamu.edu
  orcid: https://orcid.org/0009-0006-2493-0853
- family-names: Zhang
  given-names: Xianyang
  email: zhangxiany@stat.tamu.edu
preferred-citation:
  type: generic
  title: 'fastcpd: Fast Change Point Detection in R'
  authors:
  - family-names: Li
    given-names: Xingchi
    email: anthony.li@stat.tamu.edu
    orcid: https://orcid.org/0009-0006-2493-0853
  - family-names: Zhang
    given-names: Xianyang
    email: zhangxiany@stat.tamu.edu
  year: '2024'
  doi: 10.48550/arXiv.2404.05933
  publisher:
    name: arXiv
repository: https://doccstat.r-universe.dev
repository-code: https://github.com/doccstat/fastcpd
commit: 1f23c07dedd3a8b01da1b91af1747608c4d9b98d
url: https://fastcpd.xingchi.li
contact:
- family-names: Li
  given-names: Xingchi
  email: anthony.li@stat.tamu.edu
  orcid: https://orcid.org/0009-0006-2493-0853
references:
- type: conference-paper
  title: Sequential Gradient Descent and Quasi-Newton's Method for Change-Point Analysis
  authors:
  - family-names: Zhang
    given-names: Xianyang
  - family-names: Dawn
    given-names: Trisha
  year: '2023'
  collection-title: Proceedings of The 26th International Conference on Artificial
    Intelligence and Statistics
  collection-type: proceedings
  volume: '206'
  editors:
  - name: Ruiz
  - name: Francisco
  - name: Dy
  - name: Jennifer
  - name: van de Meent
  - name: Jan-Willem
  publisher:
    name: PMLR
  url: https://proceedings.mlr.press/v206/zhang23b.html
  abstract: One common approach to detecting change-points is minimizing a cost function
    over possible numbers and locations of change-points. The framework includes several
    well-established procedures, such as the penalized likelihood and minimum description
    length. Such an approach requires finding the cost value repeatedly over different
    segments of the data set, which can be time-consuming when (i) the data sequence
    is long and (ii) obtaining the cost value involves solving a non-trivial optimization
    problem. This paper introduces a new sequential updating method (SE) to find the
    cost value effectively. The core idea is to update the cost value using the information
    from previous steps without re-optimizing the objective function. The new method
    is applied to change-point detection in generalized linear models and penalized
    regression. Numerical studies show that the new approach can be orders of magnitude
    faster than the Pruned Exact Linear Time (PELT) method without sacrificing estimation
    accuracy.
  start: '1129'
  end: '1143'
  conference:
    name: Proceedings of The 26th International Conference on Artificial Intelligence
      and Statistics