Updated on 2025/04/08

Information

 

写真a

 
HIROSE KEI
 
Organization
Institute of Mathematics for Industry Division of Industrial and Mathematical Statistics Professor
Center for Polymer Interface and Molecular Adhesion Science （Concurrent）
School of Sciences Department of Mathematics（Concurrent）
Graduate School of Mathematics Department of Mathematics（Concurrent）
Joint Graduate School of Mathematics for Innovation （Concurrent）
Title
Professor
Contact information
メールアドレス
Profile
We are developing practical methods for multivariate analysis that takes the covariance structures into consideration, such as factor analysis, structural equation modeling, graphical models, and canonical discriminant analysis. Specifically, we propose a new method based on structural regularization and clustering based on prediction, develop several numerical algorithms that efficiently compute the estimate of the parameter, and investigate theoretical properties of the estimated parameters. Most of the proposed methods are available for use in the R packages. Also, I have been working on applied statistics, such as electricity demand forecasting and material properties prediction.
Homepage
External link

Research Areas

  • Informatics / Statistical science

Degree

  • Doctor of Functional Mathematics

Research History

  • 大阪大学　大学院基礎工学研究科　　（２０１１年４月〜２０１６年３月）   

Education

  • Kyushu University    

    - 2007.3

Research Interests・Research Keywords

  • Research theme： Research and development of big data analysis methods for the breakthrough of multi-scale structures

    Keyword： adhesion, multi-scale analysis

    Research period： 2018.11 - 2028.3

  • Research theme： Sparse multivariate analysis

    Keyword： Sparse estimation, factor anlaysis

    Research period： 2016.4 - 2022.3

  • Research theme： Forecast of energy consumption

    Keyword： Forecast of energy consumption

    Research period： 2016.4 - 2018.5

Awards

  • 計算機統計学会 2015年度 論文賞

    2016.6   計算機統計学会   The following paper 「Kei Hirose， Yukihiro Ogura and Hidetoshi Shimodaira. Estimating scale-free networks via the exponentiation of minimax concave penalty. Journal of the Japanese Society of Computational Statistics. 28 (1), pp.139-154, 2015」 and several other papers related to sparse multivariate anlaysis.

    　More details

    スパース多変量解析の正則化法を提案し，その理論的性質を考察した．

Papers

  • Improvement of prediction accuracy by choosing resampling distribution via cross-validation. Reviewed

    Yoshida, W., and Hirose, K.

    Behaviormetrika   52   197 - 212   2025

    　More details

    Authorship：Last author   Language：English   Publishing type：Research paper (scientific journal)  

  • Time Series Analysis under Not Missing at Random Reviewed

    Baba Yuki, Hirose Kei

    Journal of the Japan Statistical Society, Japanese Issue   53 ( 2 )   275 - 296   2024.2   （ ISSN:03895602 eISSN:21891478 ）

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：Japan Statistical Society  

    <p>Time series data often include missing values, and statistical modeling that deals with missing values is needed. Typically, a state-space model is used to impute missing values. However, this approach implicitly assumes that the missing mechanism is missing at random; thus, the estimator may be biased when the missing mechanism is not missing at random. In this study, we construct and incorporate the missing mechanism to reduce the bias of the estimator. The model parameter is estimated by the Monte Carlo Expectation-Maximization (MCEM) algorithm. Monte Carlo simulation is conducted to investigate the effectiveness of our proposed procedure.</p>

    DOI： 10.11329/jjssj.53.275

    CiNii Research

    researchmap

  • Fast same-step forecast in SUTSE model and its theoretical properties

    Wataru Yoshida, Kei Hirose

    Computational Statistics and Data Analysis   190   2024.2   （ ISSN:0167-9473 eISSN:1872-7352 ）

    　More details

    Language：Others   Publishing type：Research paper (scientific journal)   Publisher：Computational Statistics and Data Analysis  

    The problem of forecasting multivariate time series by a Seemingly Unrelated Time Series Equations (SUTSE) model is considered. The SUTSE model usually assumes that error variables are correlated. A crucial issue is that the model estimation requires heavy computational loads because of a large matrix computation, especially for high-dimensional data. To alleviate the computational issue, a two-stage procedure for forecasting is constructed. First, Kalman filtering is performed as if the error variables are uncorrelated; that is, univariate time-series analyses are conducted separately to avoid a large matrix computation. Next, the forecast value is computed by using a distribution of forecast error. The proposed algorithm is much faster than the ordinary SUTSE model because a large matrix computation is not required. Some theoretical properties of the proposed estimator are presented, and Monte Carlo simulation is performed to investigate the effectiveness of the proposed method. The usefulness of the proposed procedure is illustrated through a bus congestion data application.

    DOI： 10.1016/j.csda.2023.107861

    Web of Science

    Scopus

    researchmap

  • A Gröbner basis-based approach to factor analysis (Computer Algebra : Foundations and Applications)

    Fukasaku Ryoya, Hirose Kei, Kabata Yutaro, Teramoto Keisuke

    RIMS Kokyuroku   2255   106 - 116   2023.6   （ ISSN:18802818 ）

    　More details

    Language：Japanese   Publisher：京都大学数理解析研究所  

    CiNii Research

  • Hierarchical clustered multiclass discriminant analysis via cross-validation

    Kei Hirose, Kanta Miura, Atori Koie

    Computational Statistics and Data Analysis   178   2023.2   （ ISSN:0167-9473 eISSN:1872-7352 ）

    　More details

    Language：Others   Publishing type：Research paper (scientific journal)   Publisher：Computational Statistics and Data Analysis  

    Linear discriminant analysis (LDA) is a well-known method for multiclass classification and dimensionality reduction. However, in general, ordinary LDA does not achieve high prediction accuracy when observations in some classes are difficult to be classified. A novel cluster-based LDA method is proposed that significantly improves prediction accuracy. Hierarchical clustering is adopted, and the dissimilarity measure of two clusters is defined by the cross-validation (CV) value. Therefore, clusters are constructed such that the misclassification error rate is minimized. The proposed approach involves a heavy computational load because the CV value must be computed at each step of the hierarchical clustering algorithm. To address this issue, a regression formulation for LDA is developed and an efficient algorithm that computes an approximate CV value is constructed. The performance of the proposed method is investigated by applying it to both artificial and real datasets. The proposed method provides high prediction accuracy with fast computation from both numerical and theoretical viewpoints.

    DOI： 10.1016/j.csda.2022.107613

    Web of Science

    Scopus

    researchmap

  • Sparse and Simple Structure Estimation via Prenet Penalization

    Kei Hirose, Yoshikazu Terada

    PSYCHOMETRIKA   88 ( 4 )   1381 - 1406   2022.5   （ ISSN:0033-3123 eISSN:1860-0980 ）

    　More details

    Language：English   Publishing type：Research paper (scientific journal)   Publisher：Psychometrika  

    We propose a prenet (product-based elastic net), a novel penalization method for factor analysis models. The penalty is based on the product of a pair of elements in each row of the loading matrix. The prenet not only shrinks some of the factor loadings toward exactly zero but also enhances the simplicity of the loading matrix, which plays an important role in the interpretation of the common factors. In particular, with a large amount of prenet penalization, the estimated loading matrix possesses a perfect simple structure, which is known as a desirable structure in terms of the simplicity of the loading matrix. Furthermore, the perfect simple structure estimation via the proposed penalization turns out to be a generalization of the k-means clustering of variables. On the other hand, a mild amount of the penalization approximates a loading matrix estimated by the quartimin rotation, one of the most commonly used oblique rotation techniques. Simulation studies compare the performance of our proposed penalization with that of existing methods under a variety of settings. The usefulness of the perfect simple structure estimation via our proposed procedure is presented through various real data applications.

    DOI： 10.1007/s11336-022-09868-4

    Web of Science

    Scopus

    PubMed

    researchmap

  • Sparse multivariate regression with missing values and its application to the prediction of material properties

    Keisuke Teramoto, Kei Hirose

    INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING   123 ( 2 )   530 - 546   2022.1   （ ISSN:0029-5981 eISSN:1097-0207 ）

    　More details

    Language：English   Publishing type：Research paper (scientific journal)   Publisher：WILEY  

    In the field of materials science and engineering, statistical analysis and machine learning techniques have recently been used to predict multiple material properties from an experimental design. These material properties correspond to response variables in the multivariate regression model. In this study, we conduct a penalized maximum likelihood procedure to estimate model parameters, including the regression coefficients and covariance matrix of response variables. In particular, we employ l1-regularization to achieve a sparse estimation of The regression coefficients and inverse covariance matrix of response variables. In some cases, there may be a relatively large number of missing values in the response variables, owing to the difficulty of collecting data on material properties. We therefore propose a method that incorporates a correlation structure among the response variables into a statistical model to improve the prediction accuracy under the situation with missing values. The expectation maximization algorithm is also constructed, which enables application to a dataset with missing values in the responses. We apply our proposed procedure to real data consisting of 22 material properties.

    DOI： 10.1002/nme.6867

    Web of Science

    Scopus

    researchmap

  • Interpretable Modeling for Short- and Medium-Term Electricity Demand Forecasting

    Kei Hirose

    FRONTIERS IN ENERGY RESEARCH   9   2021.12

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    We consider the problem of short- and medium-term electricity demand forecasting by using past demand and daily weather forecast information. Conventionally, many researchers have directly applied regression analysis. However, interpreting the effect of weather on the demand is difficult with the existing methods. In this study, we build a statistical model that resolves this interpretation issue. A varying coefficient model with basis expansion is used to capture the nonlinear structure of the weather effect. This approach results in an interpretable model when the regression coefficients are nonnegative. To estimate the nonnegative regression coefficients, we employ nonnegative least squares. Three real data analyses show the practicality of our proposed statistical modeling. Two of them demonstrate good forecast accuracy and interpretability of our proposed method. In the third example, we investigate the effect of COVID-19 on electricity demand. The interpretation would help make strategies for energy-saving interventions and demand response.

    DOI： 10.3389/fenrg.2021.724780

  • Event Effects Estimation on Electricity Demand Forecasting. Reviewed International journal

    Okinaga Y, Kyogoku D, Kondo S, Nagano A, Hirose K

    Scientific Reports   11   2021.6

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • Relationship between gene regulation network structure and prediction accuracy in high dimensional regression. Reviewed International journal

    Hirose K, Wada K, Hori M,Taniguchi R

    Energies   13 ( 21 )   2020.11

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    遺伝子ネットワークと予測精度をシミュレーションし，そのソフトウェアを公開した．

  • L1正則化法に基づく因子分析および構造方程式モデリングの最近の展開 Invited Reviewed

    廣瀬慧

    計算機統計学会   2020.6

    　More details

    Language：Japanese   Publishing type：Research paper (scientific journal)  

  • Robust relative error estimation Reviewed

    Kei Hirose, Hiroki Masuda

    Entropy   20 ( 9 )   2018.8

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    Relative error estimation has been recently used in regression analysis. A crucial issue of the existing relative error estimation procedures is that they are sensitive to outliers. To address this issue, we employ the γ-likelihood function, which is constructed through γ-cross entropy with keeping the original statistical model in use. The estimating equation has a redescending property, a desirable property in robust statistics, for a broad class of noise distributions. To find a minimizer of the negative γ-likelihood function, a majorize-minimization (MM) algorithm is constructed. The proposed algorithm is guaranteed to decrease the negative γ-likelihood function at each iteration. We also derive asymptotic normality of the corresponding estimator together with a simple consistent estimator of the asymptotic covariance matrix, so that we can readily construct approximate confidence sets. Monte Carlo simulation is conducted to investigate the effectiveness of the proposed procedure. Real data analysis illustrates the usefulness of our proposed procedure.

    DOI： 10.3390/e20090632

  • Sparse factor regression via penalized maximum likelihood estimation. Reviewed International journal

    Hirose, K. and Imada, M.

    Statistical Papers   633 - 662   2018.5

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    In factor regression model, the maximum likelihood estimation suffers from three disadvantages: (i) the maximum likelihood estimates are unavailable when the number of variables exceeds the number of observations, (ii) the rotation technique based on maximum likelihood estimates produces an insufficiently sparse loading matrix, and (iii) multicollinearity can occur when the estimates of unique variances (specific variances) are small because the regression coefficients are sensitive to the inverse of unique variances. To handle these problems, we propose a penalized maximum likelihood procedure. Specifically, we impose a lasso-type penalty on the factor loadings to improve the sparseness of the solution. We also introduce a penalty on unique variances, which (given the factor scores) corresponds to the ridge penalty on the regression coefficient. Theoretical properties from a prediction viewpoint of our procedure are discussed. The effectiveness of the procedure is investigated through Monte Carlo simulations. The utility of our procedure is demonstrated on real data collected by an online questionnaire.

    DOI： 10.1007/s00362-016-0781-8

  • Readouts for echo-state networks built using locally regularized orthogonal forward regression Reviewed

    Ján Dolinský, Kei Hirose, Sadanori Konishi

    Journal of Applied Statistics   45 ( 4 )   740 - 762   2018.3

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    Echo state network (ESN) is viewed as a temporal expansion which naturally give rise to regressors of various relevance to a teacher output. We illustrate that often only a certain amount of the generated echo-regressors effectively explain the teacher output and we propose to determine the importance of the echo-regressors by a joint calculation of the individual variance contributions and Bayesian relevance using the locally regularized orthogonal forward regression (LROFR). This information can be advantageously used in a variety of ways for an analysis of an ESN structure. We present a locally regularized linear readout built using LROFR. The readout may have a smaller dimensionality than the ESN model itself, and improves robustness and accuracy of an ESN. Its main advantage is ability to determine what type of an additional readout is suitable for a task at hand. Comparison with PCA is provided too. We also propose a radial basis function (RBF) readout built using LROFR, since flexibility of the linear readout has limitations and might be insufficient for complex tasks. Its excellent generalization abilities make it a viable alternative to feed-forward neural networks or relevance-vector-machines. For cases where more temporal capacity is required we propose well studied delay&sum readout.

    DOI： 10.1080/02664763.2017.1305331

  • Robust sparse Gaussian graphical modeling Reviewed

    Kei Hirose, Hironori Fujisawa, Jun Sese

    Journal of Multivariate Analysis   161   172 - 190   2017.9

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    Gaussian graphical modeling is popular as a means of exploring network structures, such as gene regulatory networks and social networks. An L1 penalized maximum likelihood approach is often used to learn high-dimensional graphical models. However, the penalized maximum likelihood procedure is sensitive to outliers. To overcome this problem, we introduce a robust estimation procedure based on the γ-divergence. The proposed method has a redescending property, which is a desirable feature in robust statistics. The parameter estimation procedure is constructed using the Majorize-Minimization algorithm, which guarantees that the objective function monotonically decreases at each iteration. Extensive simulation studies show that our procedure performs much better than the existing methods, in particular, when the contamination ratio is large. Two real data analyses are used for illustration purposes.

    DOI： 10.1016/j.jmva.2017.07.012

  • An interpersonal sentiment quantification method applied to work relationship prediction Reviewed

    Miyuki Imada, Kei Hirose, Manabu Yoshida, Sun Yong Kim, Naoya Toyozumi, Guillaume Lopez, Yutaka Kano

    NTT Technical Review   15 ( 3 )   2017.3

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

    For a business to be successful, it is important for people in the business to consider how other people feel, that is, to consider interpersonal sentiment. Our research goal is to quantitatively predict the strength of interpersonal sentiment by analyzing a small amount of data on office employees, for example, their gender or age group, and data on events such as giving positive feedback on work done and sexual or power harassment without directly asking someone about their change in sentiment. In this article, we propose an interpersonal-sentiment-changing model for this quantification and propose two new analysis methods for developing prediction formulas. These methods can be used even if 90% of data is missing and in environments in which it is difficult to gather data in a comparatively short time. We also implement two visualization systems to predict how interpersonal sentiment changes for each event based on actual office data.

  • Graphical tool of sparse factor analysis Invited Reviewed International journal

    Yamamoto, M., Hirose, K., Nagata, H.

    Behaviormetrika   2017.1

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

  • Sparse modeling and model selection Reviewed

    Kei Hirose

    Journal of the Institute of Electronics, Information and Communication Engineers   99 ( 5 )   392 - 399   2016.5

    　More details

    Language：English   Publishing type：Research paper (scientific journal)  

▼display all

Books

  • スパース推定法による統計モデリング

    川野秀一，松井 秀俊，廣瀬 慧（Role：Joint author）

    共立出版  2018.3 

    　More details

    Responsible for pages：168ページ   Language：Japanese   Book type：Scholarly book

Presentations

  • Penalized likelihood approach in multivariate regression with missing values and its application to materials science Invited

    Hirose, K, Teramoto, K

    The 5th International Conference on Econometrics and Statistics (EcoSta 2022)  2022.6 

    　More details

    Event date： 2022.6

    Language：Others  

    Country：Other  

  • Computationally efficient forecasting algorithm in the SUTSE model and its properties

    Yoshida, W, Hirose, K

    The 5th International Conference on Econometrics and Statistics (EcoSta 2022)  2022.6 

    　More details

    Event date： 2022.6

    Language：Others  

    Country：Other  

  • Penalized likelihood factor analysis Invited

    Hirose, K

    The 51st Scientific Meeting of the Italian Statistical Society (SIS 2022)  2022.6 

    　More details

    Event date： 2022.6

    Language：Others  

    Country：Other  

  • Penalized likelihood approach in multivariate regression with missing values and its application to materials science Invited

    Hirose, K, Teramoto, K

    The 5th International Conference on Econometrics and Statistics (EcoSta 2022)  2022.6 

    　More details

    Event date： 2022.6

    researchmap

  • Penalized likelihood factor analysis Invited

    Hirose, K

    The 51st Scientific Meeting of the Italian Statistical Society (SIS 2022)  2022.6 

    　More details

    Event date： 2022.6

    researchmap

  • スパース推定の最新の展開 Invited

    廣瀬 慧, 松井 秀俊

    2022年度 応用統計学会  2022.5 

    　More details

    Event date： 2022.5

    Language：Others  

    Country：Other  

  • スパース推定の最新の展開 Invited

    廣瀬 慧, 松井 秀俊

    2022年度 応用統計学会  2022.5 

    　More details

    Event date： 2022.5

    Presentation type：Public lecture, seminar, tutorial, course, or other speech  

    researchmap

  • Sparse multivariate regression with missing values and its application to material properties prediction Invited

    Hirose, K, Teramoto, K

    IASC-ARS2022 (The 11th Conference of the IASC-ARS)  2022.2 

    　More details

    Event date： 2022.2

    Language：Others  

    Country：Other  

  • Sparse multivariate regression with missing values and its application to material properties prediction Invited

    Hirose, K, Teramoto, K

    IASC-ARS2022 (The 11th Conference of the IASC-ARS)  2022.2 

    　More details

    Event date： 2022.2

    researchmap

  • スパースモデリングによる 高次元材料データ解析 Invited

    廣瀬慧

    第179回粘着研究会例会  2021.11 

    　More details

    Event date： 2021.11

    Language：Others  

    Country：Other  

  • 適切な誤差分散推定によるモデル選択後の予測精度向上

    吉田 航, 廣瀬 慧

    2021年度 統計関連学会連合大会  2021.9 

    　More details

    Event date： 2021.9

    Language：Others  

    Country：Other  

  • 回帰モデルの合計値予測とクラスタリング

    廣瀬 慧, 増田 弘毅

    2021年度 統計関連学会連合大会  2021.9 

    　More details

    Event date： 2021.9

    Language：Others  

    Country：Other  

  • 接着強度予測のための多変量解析 Invited

    廣瀬 慧

    接着界面科学研究会第7回例会  2021.7 

    　More details

    Event date： 2021.7

    Language：Others  

    Country：Other  

  • Hierarchical multiclass discriminant analysis via cross-validation Invited

    Hirose, K. and Miura, K.

    The 4th International Conference on Econometrics and Statistics (EcoSta 2021)  2021.6 

    　More details

    Event date： 2021.6

    Language：Others  

    Country：Other  

  • 正則化因子分析とその応用 Invited

    廣瀬慧

    RIMS-IMI 合同談話会  2021.3 

    　More details

    Event date： 2021.3

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Event Effects Estimation on Electricity Load Forecasting International conference

    Hirose K

    I 2 CNER＆IMI International Workshop.  2021.1 

    　More details

    Event date： 2021.1

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • クラスタリングによる正準判別の精度向上と高速化.

    三浦完太, 廣瀬慧

    数学･数理科学専攻若手研究者のための異分野･異業種研究交流会2020  2020.10 

    　More details

    Event date： 2020.10

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 目的変数に欠損を含むデータに対する多変量重回帰モデルを用いた補完アルゴリズムについて

    寺本圭佑, 廣瀬慧

    数学･数理科学専攻若手研究者のための異分野･異業種研究交流会2020  2020.10 

    　More details

    Event date： 2020.10

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 遺伝子ネットワーク構造が予測精度に与える影響

    沖永悠一, 京極大助, 近藤聡, 永野惇, 廣瀬慧

    数学･数理科学専攻若手研究者のための異分野･異業種研究交流会2020  2020.10 

    　More details

    Event date： 2020.10

    Language：Japanese   Presentation type：Oral presentation (general)  

  • クラスタリングによる正準判別の精度向上とクロスバリデーションの高速化

    三浦完太, 廣瀬慧

    2020年度 科研費シンポジウム「多様な分野のデータに対する統計科学･機械的アプローチ」  2020.9 

    　More details

    Event date： 2020.9

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 遺伝子ネットワーク構造が予測精度に与える影響

    沖永悠一, 京極大助, 近藤聡, 永野惇, 廣瀬慧

    2020年度 科研費シンポジウム「多様な分野のデータに対する統計科学･機械的アプローチ」  2020.9 

    　More details

    Event date： 2020.9

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 電力需要予測のための統計モデルとソフトウェア

    廣瀬慧

    2020年度　統計関連学会連合大会  2020.9 

    　More details

    Event date： 2020.9

    Language：Japanese   Presentation type：Oral presentation (general)  

  • 電力需要の短期予測のための統計モデリング

    廣瀬慧, 増田弘毅

    統計関連学会連合大会  2019.9 

    　More details

    Event date： 2019.9

    Language：Japanese   Presentation type：Oral presentation (general)  

    Venue：滋賀大学   Country：Japan  

  • Cluster-based multiclass linear discriminant analysis Invited International conference

    Hirose, K., Miura, K. and Koie, A.

    The 3rd International Conference on Econometrics and Statistics (EcoSta 2019).  2019.6 

    　More details

    Event date： 2019.6

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Prenet Penalization in Factor Analysis and its Applications Invited International conference

    Hirose, K. and Terada, Y.

    International Conference on Advances in Interdisciplinary Statistics and Combinatorics.  2018.10 

    　More details

    Event date： 2018.10

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • 因子分析における単純構造推定のための正則化法とその応用 Invited

    廣瀬慧，寺田吉壱

    日本行動計量学会  2018.9 

    　More details

    Event date： 2018.9

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • 相対誤差に基づく回帰モデルのロバスト推定

    廣瀬慧，増田弘毅．

    2018 年度統計関連学会連合大会．  2018.9 

    　More details

    Event date： 2018.9

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Simple structure estimation via prenet penalization in factor analysis model Invited International conference

    Hirose, K. and Terada, Y.

    The 2nd International Conference on Econometrics and Statistics (EcoSta 2018).  2018.6 

    　More details

    Event date： 2018.6

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Prenet 正則化法による単純構造推定． Invited

    廣瀬慧

    日本地球惑星科学連合 2018 年大会  2018.5 

    　More details

    Event date： 2018.5

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Estimation of well-clustered structure via penalized maximum likelihood method in factor analysis model Invited International conference

    Hirose, K., and Terada, Y.

    10th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics 2017)  2017.12 

    　More details

    Event date： 2017.12

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • 電力取引市場における電力調達の最適化

    山口 尚哉，廣瀬 慧，堀 磨伊也，出口 喜也

    統計関連学会連合大会  2017.9 

    　More details

    Event date： 2017.9

    Language：Japanese  

    Country：Japan  

  • 因子分析における単純構造推定のための正則化法

    廣瀬慧，寺田 吉壱

    統計関連学会連合大会  2017.9 

    　More details

    Event date： 2017.9

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • 群の数が多い場合における多群線形判別

    小家 亜斗吏 廣瀬慧

    統計関連学会連合大会  2017.9 

    　More details

    Event date： 2017.9

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Perfect simple structure estimation via extension of quartimin criterion Invited International conference

    Hirose, K.

    Conference of the International Federation of Classification Societies (IFCS 2017)  2017.8 

    　More details

    Event date： 2017.8

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Robust estimation for high-dimensional Gaussian graphical models Invited International conference

    Hirose, K., Fujisawa, H.

    The 1st International Conference on Econometrics and Statistics (EcoSta 2017)  2017.6 

    　More details

    Event date： 2017.6

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • 進化計算研究者のための統計解析及び機械学習 Invited

    廣瀬慧

    第１２回進化計算学会研究会  2017.3 

    　More details

    Event date： 2017.3

    Language：Japanese   Presentation type：Oral presentation (invited, special)  

    Country：Japan  

  • 超高次元データの統計解析における最適化問題 Invited

    廣瀬慧

    OR九州支部  2017.3 

    　More details

    Event date： 2017.3

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • 正則化法によるスパース推定とその応用 Invited

    廣瀬慧

    電気学会 全国大会  2017.3 

    　More details

    Event date： 2017.3

    Language：Japanese   Presentation type：Oral presentation (general)  

    Country：Japan  

  • スパース推定法による高次元データ解析 Invited International conference

    廣瀬慧

    統計科学研究会  2016.12 

    　More details

    Event date： 2016.12

    Language：Japanese   Presentation type：Oral presentation (invited, special)  

    Country：Japan  

  • ロバストかつスパースなガウシアングラフィカルモデリングと遺伝子データへの応用

    廣瀨 慧, 藤澤　洋徳

    統計関連学会連合大会  2016.9 

    　More details

    Event date： 2016.9

    Language：Japanese   Presentation type：Oral presentation (general)  

    Venue：金沢大学   Country：Japan  

    Kanazawa University

  • Robust Estimation for Gaussian Graphical Modeling and Its Application to Gene Expression Data Invited International conference

    Hirose, K. and Fujisawa, H.

    The fifth International Conference on Continuous Optimization. National Graduate Institute for Policy Studies (GRIPS)  2016.8 

    　More details

    Event date： 2016.8

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Robust Estimation for Sparse Gaussian Graphical Modeling Invited International conference

    Hirose, K.

    The 4th Institute of Mathematical Statistics Asia Pacific Rim Meeting (IMS-APRM).  2016.6 

    　More details

    Event date： 2016.6

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • Sparse factor model via regularization and its extension to regression analysis

    Hirose, K.

    日本計算機統計学会第30回大会  2016.5 

    　More details

    Event date： 2016.5

    Language：English   Presentation type：Oral presentation (general)  

    Country：Japan  

  • 欠測がある場合におけるスパース多変量重回帰分析と物性予測への応用

    廣瀬 慧, 寺本 圭佑

    2022年度 統計関連学会連合大会  2022.9 

    　More details

    Language：Others  

    Country：Other  

  • スパース多変量解析と物性予測への応用

    廣瀬慧

    日本接着学会西部支部 令和4年度 若手主催講演会  2022.11 

    　More details

    Language：Japanese   Presentation type：Oral presentation (invited, special)  

    researchmap

  • Penalized likelihood approach in multivariate regression with missing values and its application to materials properties prediction Invited

    Hirose, K

    Statistics and Mathematical Modelling in Combination (SMMC 2022)  2022.11 

    　More details

  • 欠測がある場合におけるスパース多変量重回帰分析と物性予測への応用

    廣瀬 慧, 寺本 圭佑

    2022年度 統計関連学会連合大会  2022.9 

    　More details

▼display all

MISC

  • スパースモデリングとモデル選択

    廣瀨 慧

    電子情報通信学会誌   2016.5

    　More details

    Language：Japanese   Publishing type：Article, review, commentary, editorial, etc. (scientific journal)  

    本稿は，スパースモデリングの代表的な手法である LASSO（Least Absolute Shrinkage and Selection Operator）の理論研究に関するサーベイ記事である．まず，従来の変数選択法と LASSO との関係性を明らかした，LARS アルゴリズム（Least Angle Regression）を解説する．次に，変数の数が観測数よりも多い場合における LASSO の収束レートや変数選択の一致性に関する研究を幾つか紹介する．

  • マルチスケール構造解明のためのビッグデータ解析手法の研究開発

    廣瀬慧

    2022.2

    　More details

    Language：Others  

  • スパースモデリングの基本と応用例

    廣瀬慧

    マテリアルステージ, 技術情報協会   2022.2

    　More details

    Language：Others  

  • スパースモデリングの基本と応用例

    廣瀬慧

    マテリアルステージ, 技術情報協会   2022.2

    　More details

    Authorship：Lead author  

    researchmap

  • マルチスケール構造解明のためのビッグデータ解析手法の研究開発

    廣瀬慧

    2022.2

    　More details

  • 因子分析モデルにおける構造正則化

    廣瀬慧

    京都大学 数理解析研究所 講究録   2019.6

    　More details

    Language：Japanese   Publishing type：Internal/External technical report, pre-print, etc.  

▼display all

Works

  • Rパッケージ hclda

    三浦完太，廣瀬慧

    2021.6

    　More details

    クロスバリデーションに基づく線形判別分析のクラスタリング

  • Rパッケージ hclda

    三浦完太, 廣瀬慧

    2021.6

    　More details

    クロスバリデーションに基づく線形判別分析のクラスタリング

    researchmap

  • Rパッケージ simrnet

    沖永悠一，廣瀬慧

    2021.2

    　More details

    elastic netのシミュレーションを行うパッケージ．ネットワーク構造をも考慮する．
    elastic netのシミュレーションを行うパッケージ．ネットワーク構造をも考慮する．

  • Rパッケージ simrnet

    沖永悠一, 廣瀬慧

    2021.2

    　More details

    elastic netのシミュレーションを行うパッケージ．ネットワーク構造をも考慮する．

    researchmap

  • 電力需要予測ソフト

    廣瀬慧

    2020.6

    　More details

    JEPXのスポット市場での電力調達に使える需要予測ソフト．

  • 電力需要予測ソフト

    廣瀬慧

    2020.6

    　More details

    JEPXのスポット市場での電力調達に使える需要予測ソフト．

    researchmap

  • Rパッケージ　rsggm

    廣瀬慧

    2015.12

    　More details

    ロバストかつスパースなガウシアングラフィカルモデル

  • Rパッケージ fanc

    廣瀬慧

    2015.12

    　More details

    ロバストかつスパースなガウシアングラフィカルモデル

    researchmap

  • Rパッケージ　fanc

    廣瀬慧，山本倫生，永田晴久

    2012.5

    　More details

    正則化法による因子分析

  • Rパッケージ fanc

    廣瀬慧, 山本倫生, 永田晴久

    2012.5

    　More details

    正則化法による因子分析

    researchmap

▼display all

Industrial property rights

Patent   Number of applications: 0   Number of registrations: 0
Utility model   Number of applications: 0   Number of registrations: 0
Design   Number of applications: 0   Number of registrations: 0
Trademark   Number of applications: 0   Number of registrations: 0

Professional Memberships

  • American Statistical Association, 日本統計学会, 応用統計学会, 計算機統計学会, Bulletin of Informatics and Cybernetics

  • American Statistical Association, 日本統計学会, 応用統計学会, 計算機統計学会, Bulletin of Informatics and Cybernetics

    　 More details

Committee Memberships

  • 日本統計学会   多様性推進特別委員会   Domestic

    2021.4 - 2024.3   

  • 日本統計学会   代議員  

    2021.4 - 2023.3   

    　 More details

  • 計算機統計学会 欧文誌編集委員   編集委員   Domestic

    2015.1 - 2018.3   

Academic Activities

  • Screening of academic papers

    Role(s)： Peer review

    2023

    　More details

    Type：Peer review 

    Number of peer-reviewed articles in foreign language journals：5

    Number of peer-reviewed articles in Japanese journals：1

    Proceedings of International Conference Number of peer-reviewed papers：0

    Proceedings of domestic conference Number of peer-reviewed papers：0

  • Screening of academic papers

    Role(s)： Peer review

    2022

    　More details

    Type：Peer review 

    Number of peer-reviewed articles in foreign language journals：8

  • Screening of academic papers

    Role(s)： Peer review

    2021

    　More details

    Type：Peer review 

    Number of peer-reviewed articles in foreign language journals：6

    Number of peer-reviewed articles in Japanese journals：1

  • Screening of academic papers

    Role(s)： Peer review

    2020

    　More details

    Type：Peer review 

    Number of peer-reviewed articles in foreign language journals：12

    Number of peer-reviewed articles in Japanese journals：0

    Proceedings of International Conference Number of peer-reviewed papers：0

    Proceedings of domestic conference Number of peer-reviewed papers：0

  • Screening of academic papers

    Role(s)： Peer review

    2019

    　More details

    Type：Peer review 

    Number of peer-reviewed articles in foreign language journals：9

    Number of peer-reviewed articles in Japanese journals：0

    Proceedings of International Conference Number of peer-reviewed papers：0

    Proceedings of domestic conference Number of peer-reviewed papers：0

  • Screening of academic papers

    Role(s)： Peer review

    2018

    　More details

    Type：Peer review 

    Number of peer-reviewed articles in foreign language journals：15

  • Screening of academic papers

    Role(s)： Peer review

    2017

    　More details

    Type：Peer review 

    Number of peer-reviewed articles in foreign language journals：5

    Number of peer-reviewed articles in Japanese journals：0

    Proceedings of International Conference Number of peer-reviewed papers：0

    Proceedings of domestic conference Number of peer-reviewed papers：0

▼display all

Research Projects

  • Development of Vacancy Rate Prediction Methods for Apartments with Prediction Accuracy and Interpretability

    Grant number：23K01333  2023.4 - 2026.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    本橋 永至, 廣瀬 慧

    　 More details

    Grant type：Scientific research funding

    本研究の目的は，予測精度と解釈性を両立した共同住宅の空室率を予測する手法を開発し，共同住宅の空室率の要因を明らかにすることである．本研究では，賃貸募集情報から空室率を予測する手法を開発し，スクレイピングによって取得する実データを用いて，提案手法の有効性を検証する．提案手法は不動産投資の空室リスクを定量的に評価することを可能にするとともに，我が国の喫緊の課題である空き家問題にも貢献することが期待できる．

    CiNii Research

  • Sparse factor analysis in high-dimensional time series and its application to energy science

    Grant number：23K11007  2023 - 2025

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    廣瀬 慧

    　 More details

    Grant type：Scientific research funding

    本研究では、因子分析モデルと状態空間モデルを融合させた多変量時系列モデリングを行う。時系列データの内在する構造を理解し、新たな知識発見へとつなげるためには、推定されたモデルを解釈することが必要不可欠となる。そこで、新たな正則化項に基づくスパース正則化法を提案する。とくに、Lasso等の従来のスパース推定法だけでなく、因子分析特有のスパース推定法である因子回転を拡張することにより、全く新しいスパース正則化法を提案する。この方法が実現すると、高精度に予測し、かつ結果を解釈できる手法として、様々な科学・産業に応用できるようになる。提案手法を実行するRパッケージを作成し、Web上に公開する。

    CiNii Research

  • Mathematical properties of maximum likelihood estimators in factor analysis models via computational algebra and geometry.

    Grant number：23H04474  2023 - 2024

    Japan Society for the Promotion of Science・Ministry of Education, Culture, Sports, Science and Technology  Grants-in-Aid for Scientific Research  Grant-in-Aid for Transformative Research Areas (A)

    廣瀬 慧

    　 More details

    Authorship：Principal investigator  Grant type：Scientific research funding

    因子分析では、パラメータの最尤推定値を近似的に求めるのが一般的であるが、分散パラメータが負となる不適解問題等、解空間の次元と密接に関わっている問題がある。しかしながら、一般に、近似解から解空間の次元等を厳密に求めることは困難であるため、不適解問題等の性質を理論的に解明することは困難となる。そこで、因子分析における最尤解を厳密に求めるアルゴリズムを構築する。このようなアプローチを通じて、解空間の次元などの解の性質を明らかにできる。その結果、データの背後にある構造を正しく記述できるようになる。

    CiNii Research

  • Deepening and developing statistical theory for dependent data based on Levy noise

    Grant number：23K22410  2022.4 - 2026.3

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (B)

    増田 弘毅, 廣瀬 慧, 小池 祐太, 江口 翔一

    　 More details

    Grant type：Scientific research funding

    現代のさまざまな場面で顕在化している大規模な個体群経時データに潜む多様な特性量を定量的に推定し、推定、モデル評価、予測といった基礎的な統計解析ツールを提供するための数理基盤を創出する。モデルの確率構造を適切に捉えつつ、非正規レヴィ駆動モデルに対するエルゴード的統計および非エルゴード的統計を効果的に融することで、従来にない推測理論体系を構築する。従属性統計モデリング手法としての正規型および非正規型の擬似尤度解析を相乗的に深化させ、理論と計算のバランスがとれた統計手法を具現化する。

    CiNii Research

  • 予測モデルのグループ化を目的とするクラスター分析とその応用

    Grant number：19K11862  2019 - 2021

    Japan Society for the Promotion of Science  Grants-in-Aid for Scientific Research  Grant-in-Aid for Scientific Research (C)

    廣瀬 慧

    　 More details

    Authorship：Principal investigator  Grant type：Scientific research funding

    近年，諸科学の分野で多様性を伴うビッグデータが取得されている．入力データもしくは出力データに多様性を伴う場合，単一の回帰分析や判別分析では予測精度が高くないことが多い．そこで，複数の予測モデルを構築することが考えられるが，あまり大量に予測モデルを作りすぎてもかえって予測精度が向上しないことがある．そこで本研究では，複数の予測モデルをグループ化する．これを実現するために，予測モデルに対するクラスター分析を行う．目的関数として，予測誤差に基づく関数を定義することにより，予測精度を向上させる．このモデルに含まれるパラメータを高速に推定するために，効率的な計算アルゴリズムを提案する．

    CiNii Research

  • 材料実験データの統計解析技術

    2016.8 - 2018.7

    Joint research

    　 More details

    Authorship：Principal investigator  Grant type：Other funds from industry-academia collaboration

  • スパース正則化法に基づく探索的構造方程式モデリング

    Grant number：15K15949  2015 - 2018

    Grants-in-Aid for Scientific Research  Grant-in-Aid for Young Scientists (B)

    　 More details

    Authorship：Principal investigator  Grant type：Scientific research funding

▼display all

Class subject

  • MMA講究D

    2024.10 - 2025.3   Second semester

  • 数理科学特別講義Ⅷ

    2024.10 - 2025.3   Second semester

  • 数理統計学

    2024.10 - 2025.3   Second semester

  • 数理科学特論８

    2024.10 - 2025.3   Second semester

  • 統計的機械学習

    2024.10 - 2024.12   Fall quarter

  • 統計科学・演習

    2024.4 - 2024.9   First semester

  • 数学共創基礎Ⅰ

    2024.4 - 2024.6   Spring quarter

  • 統計数理学大意

    2023.10 - 2024.3   Second semester

  • 数学特論１５

    2023.10 - 2024.3   Second semester

  • 機械学習と人工知能

    2023.10 - 2023.12   Fall quarter

  • 数学創発モデリング

    2023.4 - 2024.3   Full year

  • 統計科学・演習

    2023.4 - 2023.9   First semester

  • 数学共創基礎Ⅰ

    2023.4 - 2023.6   Spring quarter

  • 統計数理学大意

    2022.10 - 2023.3   Second semester

  • 数学特論１５（統計数理学）

    2022.10 - 2023.3   Second semester

  • 機械学習と人工知能

    2022.10 - 2022.12   Fall quarter

  • 生命情報統計学特論

    2022.6 - 2022.8   Summer quarter

  • Bioinformatics, Advanced Course Ⅵ

    2022.6 - 2022.8   Summer quarter

  • 生命情報統計学特論

    2022.6 - 2022.8   Summer quarter

  • Bioinformatics and Statistics

    2022.6 - 2022.8   Summer quarter

  • 数理統計学

    2022.4 - 2022.9   First semester

  • 統計科学・演習

    2022.4 - 2022.9   First semester

  • 数学共創基礎Ⅰ

    2022.4 - 2022.6   Spring quarter

  • 情報統計学演習

    2021.10 - 2022.3   Second semester

  • 数理統計学

    2021.10 - 2022.3   Second semester

  • 統計数学・演習

    2021.10 - 2022.3   Second semester

  • 機械学習と人工知能

    2021.10 - 2021.12   Fall quarter

  • 生命情報統計学特論

    2021.6 - 2021.8   Summer quarter

  • 数学共創基礎Ⅰ

    2021.4 - 2021.6   Spring quarter

  • 情報数学特論3

    2020.10 - 2021.3   Second semester

  • 統計数学演習

    2020.10 - 2021.3   Second semester

  • 生命情報統計学特論

    2020.4 - 2020.9   First semester

  • 機械学習と人工知能

    2019.10 - 2020.3   Second semester

  • 共創・共創基礎プロジェクト

    2019.10 - 2020.3   Second semester

  • 情報数学特論3

    2019.10 - 2020.3   Second semester

  • 統計数学

    2019.10 - 2020.3   Second semester

  • 情報統計学基礎

    2019.4 - 2019.9   First semester

  • 数理統計学

    2019.4 - 2019.9   First semester

  • 生命情報統計学特論

    2019.4 - 2019.9   First semester

  • 数理統計

    2018.10 - 2019.3   Second semester

  • 生命情報科学II

    2018.10 - 2019.3   Second semester

  • 統計数学・演習

    2018.10 - 2019.3   Second semester

  • 情報数学特論3

    2018.10 - 2019.3   Second semester

  • 生命情報統計学特論

    2018.4 - 2018.9   First semester

  • 統計数理学基礎・演習

    2017.10 - 2018.3   Second semester

  • 生命情報統計学特論

    2017.10 - 2018.3   Second semester

  • 生命情報統計学特論

    2016.10 - 2017.3   Second semester

  • 数理統計学

    2016.10 - 2017.3   Second semester

  • 統計数理学大意

    2016.4 - 2016.9   First semester

  • 数学特論15

    2016.4 - 2016.9   First semester

  • 生命統計科学基礎

    2016.4 - 2016.9   First semester

▼display all

Visiting, concurrent, or part-time lecturers at other universities, institutions, etc.

  • 2023  関西大学ソシオネットワーク戦路研究機糖  Classification:Part-time faculty 

Outline of Social Contribution and International Cooperation activities

  • Through joint research with companies and participation in FMfI and SGW, I have developed several statistical methods that can be used for real problems. I have accomplished the social implementation of COI project.

Social Activities

  • データ解析と統計学

    福岡県教育委員会  九州大学 西新プラザ  2019.8

    　More details

    Audience：General,　Scientific,　Company,　Civic organization,　Governmental agency

    Type：Lecture

    近年、機械学習や統計解析のソフトウェアが普及し、データ解析が身近なものになりました。データ解析手法の基盤となっているのは、数学・統計学です。たとえば、データ解析手法の多くは、線形代数など基礎的な数学に基づいて構成されています。また、台風の予報などで使われる予測区間は、推定量のばらつきを評価する統計学に基づいています。
    本講義では、データ解析で用いられる様々な統計解析手法とその基盤を支える数学についてお話します。また、予測区間やモデル選択などの統計学の基礎についても説明します。