Presentation 2021-03-03
Selective Inference for Change-point Detection in Multi-dimensional Series Data
Ryota Sugiyama, Hiroki Toda, Vo Nguyen Le Duy, Yu Inatsu, Ichiro Takeuchi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Detecting changes of the average structures in a multi-dimensional sequence is an important task in various fields. In this problem, since change-points can be observed in a part of the dimensions, it is also necessary to detect the dimensions of change as well as the time points of change. Furthermore, in order to make statistical inferences on the detected change points, it is necessary to take into account the selection bias owing to the algorithm. In this study, we perform multi-dimensional change point detection using the scan statistic and propose a valid statistical inference method for the detected change points using the framework of conditional selective inference.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Change-point detection / Selective Inference
Paper # IBISML2020-51
Date of Issue 2021-02-23 (IBISML)

Conference Information
Committee IBISML
Conference Date 2021/3/2(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Organized and general sessions on machine learning
Chair Ichiro Takeuchi(Nagoya Inst. of Tech.)
Vice Chair Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Masashi Sugiyama(AIST) / Koji Tsuda(NTT)
Assistant Atsuyoshi Nakamura(Hokkaido Univ.) / Shigeyuki Oba(Miidas)

Paper Information
Registration To Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Selective Inference for Change-point Detection in Multi-dimensional Series Data
Sub Title (in English)
Keyword(1) Change-point detection
Keyword(2) Selective Inference
1st Author's Name Ryota Sugiyama
1st Author's Affiliation Nagoya Institute of Technology(NIT)
2nd Author's Name Hiroki Toda
2nd Author's Affiliation Nagoya Institute of Technology(NIT)
3rd Author's Name Vo Nguyen Le Duy
3rd Author's Affiliation Nagoya Institute of Technology(NIT)
4th Author's Name Yu Inatsu
4th Author's Affiliation Nagoya Institute of Technology(NIT)
5th Author's Name Ichiro Takeuchi
5th Author's Affiliation Nagoya Institute of Technology/RIKEN Center for Advanced Intelligence Project(NIT/RIKEN)
Date 2021-03-03
Paper # IBISML2020-51
Volume (vol) vol.120
Number (no) IBISML-395
Page pp.pp.63-70(IBISML),
#Pages 8
Date of Issue 2021-02-23 (IBISML)