Presentation 2022-07-22
An Efficient Algorithm for Optimal Decision on Piecewise Linear Regression Model by Bayes Decision Theory
Noboru Namegaya, Koshi Shimada, Toshiyasu Matsushima,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we propose a Beyes-optimal prediction method on a piecewise linear regression model by Bayes decision theory. The computation of the prediction requires weighting the posterior probability of all patterns of regression coefficient changes and all ranges of the coefficients. Especially, the computational complexity of weighting the posterior probability of all the coefficient changes is exponential order. Therefore, we propose a method of reducing the computational complexity by lumping coefficient changing patterns together if the change points before and after the data point to be predicted coincide.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Nonlinear regression model / Piecewise linear regression model / Bayesian decision theory
Paper # IT2022-25
Date of Issue 2022-07-14 (IT)

Conference Information
Committee IT
Conference Date 2022/7/21(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Okayama University of Science
Topics (in Japanese) (See Japanese page)
Topics (in English) Freshman session, General
Chair Tetsuya Kojima(Tokyo Kosen)
Vice Chair Yasuyuki Nogami(Okayama Univ.)
Secretary Yasuyuki Nogami(Saitamai Univ.)
Assistant Takayuki Nozaki(Yamaguchi Univ.)

Paper Information
Registration To Technical Committee on Information Theory
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Efficient Algorithm for Optimal Decision on Piecewise Linear Regression Model by Bayes Decision Theory
Sub Title (in English)
Keyword(1) Nonlinear regression model
Keyword(2) Piecewise linear regression model
Keyword(3) Bayesian decision theory
1st Author's Name Noboru Namegaya
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Koshi Shimada
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Toshiyasu Matsushima
3rd Author's Affiliation Waseda University(Waseda Univ.)
Date 2022-07-22
Paper # IT2022-25
Volume (vol) vol.122
Number (no) IT-128
Page pp.pp.51-55(IT),
#Pages 5
Date of Issue 2022-07-14 (IT)