International Symposium on New Developments of Theories,

Methodologies and Applications for Large Complex Data

Supported by
Grant-in-Aid for Scientific Research (A) 25H01107
"Advancement and Expansion of Theories and Methodologies for Large-Scale Complex Data"
(Principal Investigator: Makoto Aoshima)

Grant-in-Aid for Challenging Research (Exploratory) 26K23798
"Building an Innovative Platform for Real-Time Streaming Data Based on High-Dimensional, Low-Sample-Size Theory"
(Principal Investigator: Makoto Aoshima)


Date: October 21-23, 2026
Venue: iias Hall (located in iias Tsukuba https://tsukuba.iias.jp/iiashall)
5-19 Kenkyugakuen, Tsukuba, Ibaraki 305-0817, Japan
Contents & Purposes: Please look at THIS PAGE for further details.
Access: Please see THIS PAGE.
Dinner: October 22, 19:30-
Tenryu

Program Schedule (PDF)/ Flyer (PDF)

* denotes speakers

October 21

14:00-14:10 Opening

Time (UTC+9) Title and Speaker (Affiliation)
Invited Session
14:10-14:50 Enhanced Gaussian kernel k-means for high-dimensional, low-sample-size data    [Abstract]
   Kento Egashira*,a, Kazuyoshi Yatab, and Makoto Aoshimab
  a(Department of Information Science and Technology, Tokyo University of Science)
  b(Institute of Mathematics, University of Tsukuba)
15:00-15:40 A theory of nonparametric covariance function estimation for discretely observed data    [Abstract]
  Yoshikazu Terada*,a and Atsutomo Yarab
  a(Graduate School of Engineering Science, The University of Osaka / RIKEN AIP)
  b(Graduate School of Engineering Science, The University of Osaka)
15:50-16:30 Applications of the high-dimensional statistics to astrophysics and related fields    [Abstract]
  Tsutomu T. Takeuchi*,a, Yu Oganeb, Kazuyoshi Yatac, Kento Egashirad, Makoto Aoshimac, Kohji Yoshikawae, Nanase Haradaf, and Koichiro Nakanishif
  a(Division of Particle and Astrophysical Science, Nagoya University
    / The Research Center for Statistical Machine Learning, The Institute of Statistical Mathematics)
  b(Division of Particle and Astrophysical Science, Nagoya University)
  c(Institute of Mathematics, University of Tsukuba)
  d(Department of Information Science and Technology, Tokyo University of Science)
  e(Center for Computational Sciences, University of Tsukuba)
  f(National Astronomical Observatory of Japan)
16:50-17:30 A statistical framework for contrastive principal component analysis    [Abstract]
  Shao-Hsuan Wang
  (Graduate Institute of Statistics, National Central University)
17:40-18:20 A note on estimation of restricted (ordered, upper (lower)-bounded) scale parameter of Gamma distribution    [Abstract]
  Yuan-Tsung Chang*,a and Nobuo Shinozakib
  a(The Institute of Statistical Mathematics / Mejiro University)
  b(Faculty of Science and Technology, Keio University)

October 22

Time (UTC+9) Title and Speaker (Affiliation)
Young Researchers Session I
10:40-11:50
  1. Data transformation for high-dimension, strongly spiked eigenvalue models using automatic sparse estimation    [Abstract]
      Tetsuya Umino*,a, Kazuyoshi Yatab, and Makoto Aoshimab
      a(Graduate School of Science and Technology, University of Tsukuba)
      b(Institute of Mathematics, University of Tsukuba)
  2. Augmented James-Stein estimation for leading eigenvectors and eigenspaces in high dimensions    [Abstract]
       Giheon Seong*,a, Seungki Hongb, and Sungkyu Jungc
      a(Department of Statistics, Seoul National University)
      b(Meritz Fire & Marine Insurance Co., Ltd.)
      c(Department of Statistics and Institute for Data Innovation in Science, Seoul National University)
  3. Nonparametric maximum likelihood estimation of intensities for covariate-driven Poisson processes    [Abstract]
       Atsutomo Yara*,a and Yoshikazu Teradab
      a(Graduate School of Engineering Science, The University of Osaka)
      b(Graduate School of Engineering Science, The University of Osaka / RIKEN AIP)
Invited Session
12:00-12:30 A nonparametric test of spherical symmetry applicable to high dimensional data    [Abstract]
  Bilol Banerjee*,a and Anil K. Ghoshb
  a(Department of Statistics and Data Science, National University of Singapore)
  b(Theoretical Statistics and Mathematics Unit, Indian Statistical Institute, Kolkata)
12:30-14:00 Lunch
Special Invited Session
14:00-14:50 High-dimensional precision matrix quadratic forms: Estimation framework for p > n    [Abstract]
Speaker: Weiming Li
   (School of Statistics and Data Science, Shanghai University of Finance and Economics)
Discussion Leader: Kento Egashira (Department of Information Science and Technology, Tokyo University of Science)
15:05-15:55 Joint estimation of high-dimensional spiked covariance matrices via a partially shared subspace    [Abstract]
Speaker: Sungkyu Jung
   (Department of Statistics and Institute for Data Innovation in Science, Seoul National University)
Joint work with: Changwon Yoona, Minwoo Kimb, and Jeongyoun Ahna
  a(Department of Industrial and Systems Engineering, KAIST)
  b(Department of Statistics, Seoul National University)
Discussion Leader: Kazuyoshi Yata (Institute of Mathematics, University of Tsukuba)
16:10-17:00 From high-dimensional classification to clustering: High-impact feature selection via ggCGA and UL-MLR    [Abstract]
Speaker: Shih-Feng Huang
   (Graduate Institute of Statistics, National Central University)
Discussion Leader: Yuan-Tsung Chang (The Institute of Statistical Mathematics / Mejiro University)
Keynote Session
17:15-18:15 Approaching the frontier in large risky-asset universes: Direct portfolio estimation via CORE    [Abstract]
Speaker: Xinghua Zheng
   (Department of ISOM, Hong Kong University of Science and Technology)
Discussion Leader: Shogo Nakakita (Graduate School of Engineering Science, The University of Osaka)
19:30- Dinner

October 23

Time (UTC+9) Title and Speaker (Affiliation)
Young Researchers Session II
10:40-11:50
  1. Group sequential one-sample location testing for high dimensions
       Masaki Hoshino*,a, Kento Egashirab, and Hikaru Yamaguchib
      a(Graduate School of Science and Technology, Tokyo University of Science)
      b(Department of Information Science and Technology, Tokyo University of Science)
  2. Testing and segmentation of joint and individual components in integrative multi-source factor models    [Abstract]
       Kyoowon Kim*,a and Sungkyu Jungb
      a(Department of Statistics, Seoul National University)
      b(Department of Statistics and Institute for Data Innovation in Science, Seoul National University)
  3. Operator learning for functional autoregressive models    [Abstract]
       Shuntaro Suzuki*,a and Yoshikazu Teradab
      a(Graduate School of Engineering Science, The University of Osaka)
      b(Graduate School of Engineering Science, The University of Osaka / RIKEN AIP)
Invited Session
12:00-12:40 Generalization error analysis for linear binary classification under Lipschitz loss functions
  Shogo Nakakita
  (Graduate School of Engineering Science, The University of Osaka)
12:40-14:10 Lunch
14:10-14:50 Asymptotically normal estimators in high-dimensional linear regression
  Koji Tsukuda*,a and Kou Fujimorib
  a(Faculty of Mathematics, Kyushu University)
  b(Faculty of Economics and Law, Shinshu University)
15:00-15:40 Testing homogeneity of high-dimensional covariance matrices under a low-dimensional factor structure    [Abstract]
  Takahiro Nishiyama*,a, Masashi Hyodob, Shoma Yamashitac, and Nobumichi Shutohd
  a(Faculty of Science, Tokyo University of Science)
  b(Faculty of Economics, Kanagawa University)
  c(Graduate School of Science, Kobe University)
  d(Laboratory of Medical Data Sciences, Kobe Pharmaceutical University / Graduate School of Science, Kobe University)

15:40-15:45 Closing