TOHOKU UNIVERSITY Researchers

Details of the Researcher

Home

日本語 English

Mineaki Ohishi

Section

Center for Data-driven Science and Artificial Intelligence

Job title

Assistant Professor

Degree

Ph.D in Science (Hiroshima University)

researchmap

https://researchmap.jp/ohishim

J-GLOBAL ID

202001012156659562

e-Rad No.

00878291

ORCID

https://orcid.org/0000-0001-8727-3631

Researcher ID

GZH-2942-2022

Research History 5

2024/04 - Present

Tohoku University　Center for Statistical Science, Graduate School of Information Sciences
2022/11 - Present

Tohoku University　Fundamental Data Informatics, Department of Computer and Mathematical Sciences, Graduate School of Information Sciences
2022/11 - Present

Tohoku University　Center for Data-driven Science and Artificial Intelligence　Assistant Professor
2020/10 - 2022/10

Hiroshima University　Education and Research Center for Artificial Intelligence and Data Innovation　Assistant Professor (Special Appointment)
2020/04 - 2020/09

Hiroshima University　Office of Academic Research and Industry-Government Collaboration　Assistant Professor (Special Appointment)

Education 3

Hiroshima University　Graduate School of Science　Department of Mathematics Doctoral Program

2018/04 - 2021/03
Hiroshima University　Graduate School of Science　Department of Mathematics Master's Program

2016/04 - 2018/03
Hiroshima University　School of Science　Department of Mathematics

2012/04 - 2016/03

Professional Memberships 2

KES International

2020/01 - Present
The Japan Statistical Society

2017/01 - Present

Research Interests 7

Nonparametric Regression
Algorithm
Penalized Estimation
Real Estate Data Analysis
Model Selection
Sparse Estimation
Statistical Science

Research Areas 1

Informatics / Statistical science /

Awards 7

広島大学大学院理学研究科長賞

2021/03
第15回日本統計学会春季集会ポスターセッション統計検定センター長賞

2021/03
第15回日本統計学会春季集会ポスターセッション優秀発表賞

2021/03
Hiroshima University Excellent Student Scholarship for AY 2019

2019/12
行動計量学会岡山地域部会第71回研究会・第172回岡山統計研究会優秀賞

2019/03
行動計量学会岡山地域部会第67回研究会・第167回岡山統計研究会優秀賞

2018/03
行動計量学会岡山地域部会第63回研究会・第163回岡山統計研究会優秀賞

2017/03

Show all ︎Show 5

Papers 19

Generalized Degrees of Freedom for Network Lasso and Its Influence on Model Selection Peer-reviewed

Koki Kirishima, Mineaki Ohishi, Ryoya Oda, Hirokazu Yanagihara

Computational Journal of Mathematical and Statistical Sciences　5　(2)　785-818　2026/07/25
Publisher: Egyptian Knowledge Bank
DOI： 10.21608/cjmss.2026.471432.1388 　

eISSN： 2974-3443
Poisson Regression with Categorical Explanatory Variables via Lasso Using the Median as a Baseline Invited Peer-reviewed

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

Smart Innovation, Systems and Technologies　411　309-319　2025/02/07
Publisher: Springer Nature Singapore
DOI： 10.1007/978-981-97-7419-7_27 　

ISSN： 2190-3018

eISSN： 2190-3026
Coordinate descent algorithm for generalized group fused Lasso Peer-reviewed

Mineaki Ohishi, Kensuke Okamura, Yoshimichi Itoh, Hirofumi Wakaki, Hirokazu Yanagihara

Behaviormetrika　52　(1)　105-137　2025/01
Publisher: Springer Science and Business Media LLC
DOI： 10.1007/s41237-024-00233-6 　

ISSN： 0385-7417

eISSN： 1349-6964

More details Close

Abstract We deal with a model with discrete varying coefficients to consider modeling for heterogeneity and clustering for homogeneity, and estimate the varying coefficients by generalized group fused Lasso (GGFL). GGFL allows homogeneous groups to be joined together based on one-to-many relationships among groups. This makes GGFL a powerful technique, but to date there has been no effective algorithm for obtaining the solutions. Here we propose an algorithm for obtaining a GGFL solution based on the coordinate descent method, and show that a solution for each coordinate direction converges to the optimal solution. In a simulation, we show our algorithm is superior to ADMM, which is one of the popular algorithms. We also present an application to a spatial data analysis.
Generalized fused Lasso for grouped data in generalized linear models Peer-reviewed

Mineaki Ohishi

Statistics and Computing　34　(4)　124　2024/05/25
Publisher: Springer Science and Business Media LLC
DOI： 10.1007/s11222-024-10433-5 　

ISSN： 0960-3174

eISSN： 1573-1375

More details Close

Abstract Generalized fused Lasso (GFL) is a powerful method based on adjacent relationships or the network structure of data. It is used in a number of research areas, including clustering, discrete smoothing, and spatio-temporal analysis. When applying GFL, the specific optimization method used is an important issue. In generalized linear models, efficient algorithms based on the coordinate descent method have been developed for trend filtering under the binomial and Poisson distributions. However, to apply GFL to other distributions, such as the negative binomial distribution, which is used to deal with overdispersion in the Poisson distribution, or the gamma and inverse Gaussian distributions, which are used for positive continuous data, an algorithm for each individual distribution must be developed. To unify GFL for distributions in the exponential family, this paper proposes a coordinate descent algorithm for generalized linear models. To illustrate the method, a real data example of spatio-temporal analysis is provided.
Additive Poisson regression via forced categorical covariates and generalized fused Lasso Invited Peer-reviewed

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

Procedia Computer Science　225　1987-1996　2023/12/08
Publisher: Elsevier BV
DOI： 10.1016/j.procs.2023.10.189 　

ISSN： 1877-0509
An ℓ_{2,0}-norm constrained matrix optimization via extended discrete ﬁrst-order algorithms Peer-reviewed

Ryoya Oda, Mineaki Ohishi, Yuya Suzuki, Hirokazu Yanagihara

Hiroshima Mathematical Journal　53　(3)　251-267　2023/11/01
Publisher: Hiroshima University - Department of Mathematics
DOI： 10.32917/h2021058 　

ISSN： 0018-2079
Spatio-Temporal Analysis of Rates Derived from Count Data Using Generalized Fused Lasso Poisson Model Invited Peer-reviewed

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

Intelligent Decision Technologies　352　225-234　2023/05/30
Publisher: Springer Nature Singapore
DOI： 10.1007/978-981-99-2969-6_20 　

ISSN： 2190-3018

eISSN： 2190-3026
Geographically Weighted Sparse Group Lasso: Local and Global Variable Selections for GWR Invited Peer-reviewed

Mineaki Ohishi, Koki Kirishima, Kensuke Okamura, Yoshimichi Itoh, Hirokazu Yanagihara

Intelligent Decision Technologies　352　183-192　2023/05/30
Publisher: Springer Nature Singapore
DOI： 10.1007/978-981-99-2969-6_16 　

ISSN： 2190-3018

eISSN： 2190-3026
trec: An R package for trend estimation and classification to support integrated ecosystem assessment of the marine ecosystem and environmental factors Peer-reviewed

Hiroko Kato Solvang, Mineaki Ohishi

SoftwareX　21　101309　2023/02
Publisher: Elsevier BV
DOI： 10.1016/j.softx.2023.101309 　

ISSN： 2352-7110
Stable Estimation of the Slant Parameter in Skew Normal Regression via an MM Algorithm and Ridge Shrinkage Peer-reviewed

Mineaki Ohishi, Hirokazu Yanagihara, Hirofumi Wakaki, Masahiko Ono

International Journal of Knowledge Engineering and Soft Data Paradigms (in press)　2023
Publisher: Inderscience Publishers
DOI： 10.1504/ijkesdp.2023.10057725 　

ISSN： 1755-3210

eISSN： 1755-3229
Coordinate descent algorithm of generalized fused Lasso logistic regression for multivariate trend filtering Peer-reviewed

Ohishi, M., Yamamura, M., Yanagihara, H.

Japanese Journal of Statistics and Data Science　5　(2)　535-551　2022/12
Publisher: Springer Science and Business Media LLC
DOI： 10.1007/s42081-022-00162-2 　

ISSN： 2520-8764

eISSN： 2520-8764
Coordinate optimization for generalized fused Lasso Peer-reviewed

Ohishi, M., Fukui, K., Okamura, K., Itoh, Y., Yanagihara, H.

Communications in Statistics - Theory and Methods　50　(24)　5955-5973　2021/12/17
Publisher: Informa UK Limited
DOI： 10.1080/03610926.2021.1931888 　

ISSN： 1532-415X 0361-0926

eISSN： 1532-415X
Spatio-temporal adaptive fused Lasso for proportion data Invited Peer-reviewed

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

Intelligent Decision Technologies　238　479-489　2021/07
Publisher: Springer Singapore
DOI： 10.1007/978-981-16-2765-1_40 　

ISSN： 2190-3018

eISSN： 2190-3026
Optimizations for categorizations of explanatory variables in linear regression via generalized fused Lasso Invited Peer-reviewed

Mineaki Ohishi, Kensuke Okamura, Yoshimichi Itoh, Hirokazu Yanagihara

Intelligent Decision Technologies　238　457-467　2021/07
Publisher: Springer Singapore
DOI： 10.1007/978-981-16-2765-1_38 　

ISSN： 2190-3018

eISSN： 2190-3026
Ridge parameters optimization based on minimizing model selection criterion in multivariate generalized ridge regression Peer-reviewed

Ohishi, M.

Hiroshima Mathematical Journal　51　(2)　177-226　2021/07/01
Publisher: Hiroshima University - Department of Mathematics
DOI： 10.32917/h2020104 　

ISSN： 0018-2079
Equivalence between adaptive Lasso and generalized ridge estimators in linear regression with orthogonal explanatory variables after optimizing regularization parameters Peer-reviewed

Ohishi, M., Yanagihara, H., Kawano, S.

Annals of the Institute of Statistical Mathematics　72　(6)　1501-1516　2020/12
Publisher: Springer Science and Business Media LLC
DOI： 10.1007/s10463-019-00734-2 　

ISSN： 0020-3157

eISSN： 1572-9052
A fast optimization method for additive model via partial generalized ridge regression Invited Peer-reviewed

Keisuke Fukui, Mineaki Ohishi, Mariko Yamamura, Hirokazu Yanagihara

Intelligent Decision Technologies　193　279-290　2020/06
Publisher: Springer Singapore
DOI： 10.1007/978-981-15-5925-9_24 　

ISSN： 2190-3018

eISSN： 2190-3026
Optimization of generalized $$C_p$$ criterion for selecting ridge parameters in generalized ridge regression Invited Peer-reviewed

Mineaki Ohishi, Hirokazu Yanagihara, Hirofumi Wakaki

Intelligent Decision Technologies　193　267-278　2020/06
Publisher: Springer Singapore
DOI： 10.1007/978-981-15-5925-9_23 　

ISSN： 2190-3018

eISSN： 2190-3026
A fast algorithm for optimizing ridge parameters in a generalized ridge regression by minimizing a model selection criterion Peer-reviewed

Ohishi, M., Yanagihara, H., Fujikoshi, Y.

Journal of Statistical Planning and Inference　204　187-205　2020/01

DOI： 10.1016/j.jspi.2019.04.010 　

ISSN： 0378-3758

Show all ︎Show first 5

Misc. 22

KOO法に基づくカテゴリ変数の選択と統合

大石峰暉

統計関連学会連合大会講演報告集　2026　2026
Model Selection Methods for 3mGMANOVA Model

門田麗, 大石峰暉, 小田凌也

統計関連学会連合大会講演報告集　2026　2026
Hierarchical overlapping group Lasso for GMANOVA model

Mineaki Ohishi, Isamu Nagai, Ryoya Oda, Hirokazu Yanagihara

arXiv 2510.19311　2025/10/23

More details Close

This paper deals with the GMANOVA model with a matrix of polynomial basis functions as a within-individual design matrix. The model involves two model selection problems: the selection of explanatory variables and the selection of the degrees of the polynomials. The two problems can be uniformly addressed by hierarchically incorporating zeros into the vectors of regression coefficients. Based on this idea, we propose hierarchical overlapping group Lasso (HOGL) to perform the variable and degree selections simultaneously. Importantly, when using a polynomial basis, fitting a highdegree polynomial often causes problems in model selection. In the approach proposed here, these problems are handled by using a matrix of orthonormal basis functions obtained by transforming the matrix of polynomial basis functions. Algorithms are developed with optimality and convergence to optimize the method. The performance of the proposed method is evaluated using numerical simulation.
KOO Method-based Consistent Clustering for Group-wise Linear Regression with Graph Structure

M. Ohishi, R. Oda

arXiv 2509.11103　2025/09/14

More details Close

The kick-one-out (KOO) method is a variable selection method based on a model selection criterion. The method is very simple, and yet it has consistency in variable selection under a high-dimensional asymptotic framework with a specific model selection criterion. This paper proposes the join-twotogether (JTT) method, which is a clustering method based on the KOO method for group-wise linear regression with graph structure. The JTT method formulates the clustering problem as an edge selection problem for a graph and determines whether to select each edge based on the KOO method. We can employ network Lasso to perform such a clustering. However, network Lasso is somewhat cumbersome because there is no good algorithm for solving the associated optimization problem and the tuning is complicated. Therefore, by deriving a model selection criterion such that the JTT method has consistency in clustering under a high-dimensional asymptotic framework, we propose a simple yet powerful method that outperforms network Lasso.
KOO法に基づくグループごとに異なる回帰係数を持つ線形回帰モデルのクラスタリング

大石峰暉, 小田凌也

統計関連学会連合大会講演報告集　2025　2025
Network Lasso の一般化自由度とモデル選択への影響

桐島功希, 大石峰暉, 小田凌也

統計関連学会連合大会講演報告集　2025　2025
サッカーの途中出場選手に関する試合状況別のパフォーマンス評価

藤岡輝, 迫田智洋, 小野真彦, 大石峰暉, 門田麗

2024年度スポーツデータサイエンスコンペティション研究報告集　2025
Network Lasso のための最適化法の比較

桐島功希, 大石峰暉, 小田凌也, 栁原宏和

統計関連学会連合大会講演報告集　2024　2024
欠損データに対する fused Lasso の最適化について

大石峰暉, 栁原宏和

統計関連学会連合大会講演報告集　2024　2024
Comparison of generalized ridge regression with non-negative ridge parameters and allowance of negative ridge parameters

小野真彦, 栁原宏和, 小田凌也, 大石峰暉

統計関連学会連合大会講演報告集　2024　2024
Estimation of spatial effects by generalized fused Lasso for nonuniformly sampled spatial data: an analysis of the body condition of common minke whales (Balaenoptera acutorostrata acutorostrata) in the Northeast Atlantic

Mariko Yamamura, Hirokazu Yanagihara, Mineaki Ohishi, Keisuke Fukui, Hiroko Solvang, Nils Øien, Tore Haug

Hiroshima Statistical Research Group Technical Report, TR-No. 23-05　2023/07
線形回帰モデルにおけるカテゴリ変数の選択

大石峰暉, 栁原宏和

統計関連学会連合大会講演報告集　2023　2023
説明変数の個数が標本数を越える場合での一般化リッジ回帰におけるリッジパラメータ最適化法の比較

桐島功希, 大石峰暉, 小田凌也, 栁原宏和

統計関連学会連合大会講演報告集　2023　2023
階層的グループ Lasso による GMANOVA モデルの変数選択と次数選択

大石峰暉, 永井勇, 小田凌也, 栁原宏和

統計関連学会連合大会講演報告集　2022　2022
Generalized fused Lassoによる説明変数のカテゴリの最適化

大石峰暉, 岡村健介, 伊藤嘉道, 柳原宏和

統計関連学会連合大会講演報告集　2021　2021
Best subset selection in multivariate linear regressions via discreate first-order algorithms

2019　2019
Estimation of Geographically Varying Coefficient Model via Group Fused Lasso

2019　2019
Variable Selection Method for Nonparametric Varying Coefficient Model via Group-lasso Penalty

2019　2019
Fused Lassoを用いた地域分類~マンションの賃料に対する地域効果のモデリング~

大石峰暉, 福井敬祐, 岡村健介, 伊藤嘉道, 栁原宏和

統計関連学会連合大会講演報告集　2018　2018
Equivalence between Adaptive-Lasso and Generalized Ridge Estimates in Linear Regression with Orthogonal Explanatory Variables after Optimizing Regularization Parameters

2017　2017
Minimization algorithm of model selection criterion for optimizing tuning parameter in Lasso estimator when explanatory variables are orthogonal

Ohishi, M., Yanagihara, H.

RIMS Kôkyûroku　2047　124-140　2017
一般化リッジ回帰におけるリッジパラメータ選択のための情報量規準最小化問題の解析解

大石峰暉, 栁原宏和, 藤越康祝

統計関連学会連合大会講演報告集　2016　2016

Show all ︎Show first 5

Presentations 58

KOO法に基づくカテゴリ変数の選択と統合

大石峰暉

2026年度統計関連学会連合大会　2026/09/08
Model Selection Methods for 3mGMANOVA Model

2026/09/07
Group-Lasso for three-mode GMANOVA model with unknown item structure

Rei Monden, Mineaki Ohishi, Ryoya Oda, Hirokazu Yanagihara

The International Meeting of the Psychometric Society 2026　2026/07/24
線形回帰モデルにおけるモデル選択と Kick-one-out 法の一致性 Invited

大石峰暉

岡山統計研究会第185回研究会 (学生セッション) 全体レクチャー　2026/03/19
KOO法に基づくグループごとに異なる回帰係数を持つ線形回帰モデルのクラスタリング

大石峰暉, 小田凌也

2025年度統計関連学会連合大会　2025/09/10
Network Lasso の一般化自由度とモデル選択への影響

桐島功希, 大石峰暉, 小田凌也

2025年度統計関連学会連合大会　2025/09/09
サッカーの途中出場選手に関する試合状況別のパフォーマンス評価

藤岡輝, 迫田智洋, 小野真彦, 大石峰暉, 門田麗

2024年度スポーツデータサイエンスコンペティション　2025/01/12
Optimization of generalized fused Lasso in generalized linear models Invited

Mineaki Ohishi

The CSAT-JSS-KSS Joint Meeting in Joint Meeting of the IASC-ARS Interim Conference 2024 and CSAT 2024　2024/12/14
Network Lasso のための最適化法の比較

桐島功希, 大石峰暉, 小田凌也, 栁原宏和

2024年度統計関連学会連合大会　2024/09/03
欠損データに対する fused Lasso の最適化について.

大石峰暉, 栁原宏和

2024年度統計関連学会連合大会　2024/09/03
Comparison of generalized ridge regression with non-negative ridge parameters and allowance of negative ridge parameters

小野真彦, 栁原宏和, 小田凌也, 大石峰暉

2024年度統計関連学会連合大会　2024/09/03
Applicability of TreeSHAP to analyze real estate data Invited

Koki Kirishima, Mineaki Ohishi, Ryoya Oda, Kensuke Okamura, Yoshimichi Itoh, Hirokazu Yanagihara

The 26th International Conference on COMPUTATIONAL STATISTICS　2024/08/29
On Lasso Poisson regression for categorical variables Invited

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

The 26th International Conference on COMPUTATIONAL STATISTICS　2024/08/29
Poisson regression with categorical explanatory variables via Lasso using the median as a baseline Invited

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

The 16th International KES Conference on Intelligent Decision Technologies　2024/06/21
ネットワーク Lasso の最適化について

大石峰暉

第6回青葉山統計科学セミナー　2024/05/22
On the variable selection and prediction by geographically weighted sparse group Lasso

大石峰暉

統計数理研究所共同利用 2023年度重点型研究研究集会「高次元データ解析・スパース推定法・モデル選択法の開発と融合」　2024/03/08
Kick-one-out 法に基づいた回帰におけるクラスタリング

大石峰暉

2023年度科研費シンポジウム「統計科学・機械学習・情報数学の最前線」　2024/01/26
線形回帰モデルのカテゴリ変数に対するカテゴリ選択と変数選択

大石峰暉

2023年度科研費シンポジウム「データサイエンスにおける統計的理論・方法論の新展開」　2023/11/13
Additive Poisson regression via forced categorical covariates and generalized fused Lasso Invited

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

The 27th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems　2023/09/07
線形回帰モデルにおけるカテゴリ変数の選択

大石峰暉, 栁原宏和

2023年度統計関連学会連合大会　2023/09/04
説明変数の個数が標本数を越える場合での一般化リッジ回帰におけるリッジパラメータ最適化法の比較

桐島功希, 大石峰暉, 小田凌也, 栁原宏和

2023年度統計関連学会連合大会　2023/09/04
Comparison of prediction methods for spatial data using real estate data Invited

Koki Kirishima, Mineaki Ohishi, Hirokazu Yanagihara

The 25th International Conference on COMPUTATIONAL STATISTICS　2023/08/25
Clustering for category variables in linear regression via generalized fused Lasso Invited

Mineaki Ohishi, Hirokazu Yanagihara

The 25th International Conference on COMPUTATIONAL STATISTICS　2023/08/25
Variable selection and prediction for geographically weighted regression

Mineaki Ohishi

The 9th CWRU×TOHOKU Joint Workshop　2023/08/07
Geographically weighted sparse group Lasso: local and global variable selections for GWR Invited

Mineaki Ohishi, Koki Kirishima, Kensuke Okamura, Yoshimichi Itoh, Hirokazu Yanagihara

The 15th International KES Conference on Intelligent Decision Technologies　2023/06/14
Spatio-temporal analysis of rates derived from count data using generalized fused Lasso Invited

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

The 15th International KES Conference on Intelligent Decision Technologies　2023/06/14
Estimation of spatial effects by generalized fused Lasso for nonuniformly sampled spatial data using body condition data set from common minke whales Invited

Hirokazu Yanagihara, Mariko Yamamura, Mineaki Ohishi, Keisuke Fukui, Hiroko Solvang, Nils Øien, Tore Haug

IMR-Waseda Workshop: Advances in pragmatic computational methodologies for fish stock assessment, human impact, and environmental factor on marine ecosystems　2023/03/29
Sparse group Lasso による地理的加重回帰の局所的かつ大域的な変数選択

大石峰暉, 桐島功希, 岡村健介, 伊藤嘉道, 栁原宏和

研究集会 "多変量統計学・統計的モデル選択の新展開"　2023/03/17
階層的グループ Lasso による GMANOVA モデルの変数選択と次数選択

大石峰暉, 永井勇, 小田凌也, 栁原宏和

2022年度統計関連学会連合大会　2022/09/05
一般化 Group Fused Lasso 最適化のためのベクトル差分ノルム型罰則付き二次形式の最小化アルゴリズム

栁原宏和, 大石峰暉, 岡村健介, 伊藤嘉道, 若木宏文

広島統計グループ金曜セミナー　2021/11/26
Generalized fused Lasso による説明変数のカテゴリの最適化

大石峰暉, 岡村健介, 伊藤嘉道, 栁原宏和

2021年度統計関連学会連合大会　2021/09/08
Generalized fused Lasso ロジスティック回帰の最適化と時空間分析

大石峰暉, 山村麻理子, 栁原宏和

広島統計グループ金曜セミナー　2021/07/02
Optimizations for categorizations of explanatory variables in linear regression via generalized fused Lasso Invited

Mineaki Ohishi, Kensuke Okamura, Yoshimichi Itoh, Hirokazu Yanagihara

The 13th KES International Conference on Intelligent Decision Technologies　2021/06/16
Spatio-temporal adaptive fused Lasso for proportion data Invited

Mariko Yamamura, Mineaki Ohishi, Hirokazu Yanagihara

The 13th KES International Conference on Intelligent Decision Technologies　2021/06/16
ロジスティック回帰モデルにおける generalized fused Lasso の座標降下法

大石峰暉, 山村麻理子, 栁原宏和

第15回日本統計学会春季集会
Optimization of generalized Cp criterion for selecting ridge parameters in generalized ridge regression Invited

Mineaki Ohishi, Hirokazu Yanagihara, Hirofumi Wakaki

The 12th KES International Conference on Intelligent Decision Technologies　2020/06/19
A fast optimization method for additive model via partial generalized ridge regression Invited

Keisuke Fukui, Mineaki Ohishi, Mariko Yamamura, Hirokazu Yanagihara

The 12th KES International Conference on Intelligent Decision Technologies　2020/06/19
多変量線形回帰における discrete first-order algorithm を用いた変数選択法の提案

鈴木裕也, 大石峰暉, 小田凌也, 栁原宏和

広島統計グループ金曜セミナー　2019/12/20
Estimation of geographically varying coefficient model via group fused Lasso

大石峰暉, 福井敬祐, 岡村健介, 伊藤嘉道, 栁原宏和

2019年度統計関連学会連合大会　2019/09/09
Variable selection method for nonparametric varying coefficient model via group lasso penalty

福井敬佑, 大石峰暉, 小田凌也, 岡村健介, 伊藤嘉道, 栁原宏和

2019年度統計関連学会連合大会　2019/09/10
Best subset selection in multivariate linear regressions via discrete first-order algorithms

鈴木裕也, 大石峰暉, 小田凌也, 栁原宏和

2019年度統計関連学会連合大会　2019/09/10
偏りのある空間データに対する空間効果の推定法

大石峰暉, 福井敬祐, 岡村健介, 伊藤嘉道, 栁原宏和

統計サマーセミナー2019　2019/08/06
マンションの賃料に対する地域効果の推定法の比較

大石峰暉, 福井敬祐, 岡村健介, 伊藤嘉道, 栁原宏和

行動計量学会岡山地域部会第71回研究会・第172回岡山統計研究会 (学生セッション)　2019/03/16
generalized Lasso を用いた地域効果のクラスタリング

大石峰暉, 福井敬祐, 岡村健介, 伊藤嘉道, 栁原宏和

広島統計グループ金曜セミナー　2019/02/08
Fused Lasso を用いた地域分類～マンションの賃料に対する地域効果のモデリング～

大石峰暉, 福井敬祐, 岡村健介, 伊藤嘉道, 栁原宏和

2018年度統計関連学会連合大会　2018/09/10
A fast algorithm for solving model selection criterion minimization problem in generalized ridge

Mineaki Ohishi, Hirokazu Yanagihara

IMS - Asia Pacific Rim Meeting 2018　2018/06/27
Fused Lasso によるマンション賃料の地域効果クラスタリング

大石峰暉

行動計量学会岡山地域部会第67回研究会・第167回岡山統計研究会 (学生セッション)　2018/03/17
Clustering of regional effects in apartment rents by fused Lasso

大石峰暉, 福井敬祐, 岡村健介, 伊藤嘉道, 栁原宏和

第12回日本統計学会春季集会　2018/03/04
Equivalence under optimal regularization parameters between generalized ridge and adaptive-Lasso estimates in linear regression with orthogonal explanatory variables

Mineaki Ohishi, Hirokazu Yanagihara

Hiroshima Statistics Study Group seminars　2017/11/24
Equivalence between adaptive-Lasso and generalized ridge estimates in linear regression with orthogonal explanatory variables after optimizing regularization parameters

Mineaki Ohishi, Hirokazu Yanagihara

Capital Normal University-Hiroshima University Joint conference on Mathematics　2017/09/21
Equivalence between adaptive-Lasso and generalized ridge estimates in linear regression with orthogonal explanatory variables after optimizing regularization parameters

大石峰暉, 栁原宏和

2017年度統計関連学会連合大会　2017/09/04
罰則付き推定法の正則化パラメータ最適化

大石峰暉

統計サマーセミナー2017　2017/08/06
直交する説明変数の下での線形回帰モデルにおける一般化リッジ型 L_2 ペナルティと Adaptive-Lasso 型 L_1 ペナルティでの最適な回帰係数の同等性

大石峰暉

行動計量学会岡山地域部会第63回研究会・第163回岡山統計研究会 (学生セッション)　2017/03/18
リッジパラメータ選択のための GCV 最小化問題における罰則項の比較

大石峰暉, 栁原宏和

RIMS共同研究: Bayes Inference and Its Related Topics 研究会　2017/03/08
Equivalence between optimized regression coefficients by adaptive-Lasso type L1 penalty and generalized ridge type L2 penalty in linear regression with orthogonal explanatory variables

大石峰暉, 栁原宏和

第11回日本統計学会春季集会　2017/03/05
一般化リッジ回帰におけるリッジパラメータ選択のための情報量規準最小化問題

大石峰暉, 栁原宏和, 藤越康祝

広島統計グループ金曜セミナー　2016/12/16
主成分回帰におけるLassoのチューニングパラメータ選択のための GCV 最小化問題

大石峰暉

研究集会 "統計的推論における最近の展開"　2016/12/04
一般化リッジ回帰におけるリッジパラメータ選択のための情報量規準最小化問題の解析解

大石峰暉, 栁原宏和, 藤越康祝

2016年度統計関連学会連合大会　2016/09/07

Show all Show first 5

Research Projects 8

Development of clustering method based on kick-one-out-method

Mineaki Ohishi

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists

Category: Grant-in-Aid for Early-Career Scientists

Institution: Tohoku University

2025/04 - 2028/03
Spatio-temporal risk models for Hiroshima and Nagasaki exposures by Fused-lasso

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research

Category: Grant-in-Aid for Scientific Research (B)

2020/04/01 - 2025/03/31
Development of consistent variable selection methods in high-dimensional multivariate models Competitive

Hirokazu Yanagihara, Yoshiyuki Ninomiya, Ryoya Oda, Mineaki Ohishi

Offer Organization: The Institute of Statistical Mathematics

System: Cooperative Research Program

Category: General Cooperative Research 2

Institution: The Institute of Statistical Mathematics

2024/04 - 2025/03
Development of spatial statistical method using discrete varying coefficient model based on fused Lasso

Offer Organization: Japan Society for the Promotion of Science

System: Grants-in-Aid for Scientific Research Grant-in-Aid for Early-Career Scientists

Category: Grant-in-Aid for Early-Career Scientists

Institution: Hiroshima University

2021/04 - 2025/03
On the prediction problem for sparse group Lasso in geographically weighted regression

Mineaki Ohishi

Offer Organization: The Institute of Statistical Mathematics

System: Cooperative Research Program

Category: Specially Promoted Research

2023/04 - 2024/03
A statistical spatiotemporal estimation method for integrated ecosystem assessment in the Barents Sea

Offer Organization: Japan Society for the Promotion of Science

System: Bilateral Probram

2021/04 - 2024/03
Asymptotically loss efficiency of model selection criteria under the hybrid high-dimensional asymptotic framework

Ryoya Oda, Hirokazu Yanagihara, Mineaki Ohishi

Offer Organization: The Institute of Statistical Mathematics

System: Cooperative Research Program

Category: Specially Promoted Research

2022/04 - 2023/03
Unification of regularization parameters by weighted penalties

Mineaki Ohishi, Hirokazu Yanagihara, Ryoya Oda

Offer Organization: The Institute of Statistical Mathematics

System: Cooperative Research Program

Category: Specially Promoted Research

2022/04 - 2023/03

Show all Show first 5

Teaching Experience 3

データ科学・AI 概論　東北大学
情報教育特別講義 (AI・データ科学研究の現場)　東北大学
データ科学特論 I "スパース推定とそのモデリング" (第6回)　大阪大学 (集中講義)

Works 8

R package HOGLgmanova

Mineaki Ohishi

2025/10/23 - Present

Type: Software
R package JTT

Mineaki Ohishi

2025/09/16 - Present

Type: Software
R package GFLglm

Mineaki Ohishi

Github 2024/04/10 - Present

Type: Software
R package amgfl

Mineaki Ohishi, Keisuke Fukui, Hirokazu Yanagihara

Github 2023/07/31 - Present

Type: Software
R package GRRMSC

Mineaki Ohishi

Github 2022/04/05 - Present

Type: Software
R package GGFL

Mineaki Ohishi

Github 2022/02/02 - Present

Type: Software
R package trec

Mineaki Ohishi, Hiroko Kato Solvang

Github 2021/12/09 - Present

Type: Software
R package GFLlogit

Mineaki Ohishi

Github 2021/09/30 - Present

Type: Software

Show all ︎Show first 5

Social Activities 3

シンポジウム「未来を担うAIMD人材育成と地域社会の課題解決」

2025/12/16 - 2025/12/16
シンポジウム「情報・データ科学教育の現在とこれから ~産学における DX 活用と教育実践~」

2024/12/04 - 2024/12/04
シンポジウム「AIMD教育の水平展開と最新AI技術の教育利活用」

2023/12/21 - 2023/12/21

Academic Activities 9

2025年度統計関連学会連合大会モデル選択 (2)

2025/09/09 - 2025/09/09
2024年度統計関連学会連合大会モデル選択

2024/09/03 - 2024/09/03

Activity type: Academic society, research group, etc.
Japanese Journal of Statistics and Data Science

Activity type: Peer review
Statistics and Computing

Activity type: Peer review
International KES Conference on Intelligent Decision Technologies

Activity type: Peer review
Behaviormetrika

Activity type: Peer review
SoftwareX

Activity type: Peer review
Journal of computational and applied mathematics

Activity type: Peer review
Environmental and ecological statistics

Activity type: Peer review

Show all Show first 5

Other 2

ベースボールアナリスト 3 級
中学校・高等学校教諭専修免許状 (数学)