Bio

• 2024-present. PhD student in Econometrics and Statistics at The University of Chicago, Booth School of Business. Advisor: Tengyuan Liang.
• 2022-2024. PhD student in Statistics at Rutgers University. Advisor: Pierre C. Bellec.
• 2018-2022. BE in Mathematical Engineering, The University of Tokyo, MEIP.
• 2021-2022. Student researcher at RIKEN CBS

I have broad interests in mathematical theory and algorithms. In recent years, my research has focused on: (1) Mean-field high dimensional statistics (2) High-dimensional probability, and (3) Combinatorial stochastic processes. More recently, I have been studying optimal transport and learning theory.

Preprints

• Asymptotic Inference for Exchangeable Gibbs Partitions
  Takuya Koriyama
  arXiv:2506.21527, 2025, submitted.

• Denoising Diffusions with Optimal Transport: Localization, Curvature, and Multi-Scale Complexity
  Tengyuan Liang, Kulunu Dharmakeerthi, and Takuya Koriyama
  arXiv:2411.01629, 2024, submitted.

• Precise Asymptotics of Bagging Regularized M-estimators
  Takuya Koriyama, Pratik Patil, Jin-Hong Du, Kai Tan, and Pierre C. Bellec
  arXiv:2409.15252, 2024, major revision at Annals of Statistics. [github]

• Asymptotics of resampling without replacement in robust and logistic regression
  Pierre C. Bellec and Takuya Koriyama (alphabetical order)
  arXiv:2404.02070, 2024, major revision at Bernoulli.

• Existence of solutions to the nonlinear equations characterizing the precise error of M-estimators
  Pierre C. Bellec and Takuya Koriyama (alphabetical order)
  arXiv:2312.13254, 2023, submitted. [slide]

Publications

• Phase transitions for the existence of unregularized M-estimators in single index models
  Takuya Koriyama and Pierre C. Bellec
  Accepted to Proceedings of the 42nd International Conference on Machine Learning (ICML 2025).

• Asymptotic mixed normality of maximum likelihood estimator for Ewens–Pitman partition
  Takuya Koriyama, Takeru Matsuda and Fumiyasu Komaki
  arXiv:2207.01949, 2022, to appear in Advances in Applied Probability 58.1, 2026. [slide].

• Error estimation and adaptive tuning for unregularized robust M-estimator
  Pierre C. Bellec and Takuya Koriyama (alphabetical order)
  Journal of Machine Learning Research 26 (16), 1-40, 2025.

• Corrected generalized cross-validation for finite ensembles of penalized estimators
  Pierre C. Bellec, Jin-Hong Du, Takuya Koriyama, Pratik Patil and Kai Tan (alphabetical order)
  Journal of the Royal Statistical Society Series B: Statistical Methodology, 87(2), 289-318, 2025. [journal], [slide], [github].

• Fully Data-driven Normalized and Exponentiated Kernel Density Estimator with Hyvärinen Score
  Shunsuke Imai, Takuya Koriyama, Shouto Yonekura, Shonosuke Sugasawa and Yoshihiko Nishiyama
  Journal of Business & Economic Statistics 43 (1), 110-121, 2025. [journal]

Award

• IMS Hannan Graduate Student Travel Award, 2025.
• Travel award at Yale FDS workshop, 2024.
• Best Ph.D. Qualifying Exam Performance, Department of Statistics, Rutgers University, 2023.
• Student Travel Award, IMS International Conference on Statistics and Data Science, 2022.
• Best Presentation Award and Japan Statistical Society Certificate Director’s Award, 16th Japan Statistical Society Spring Meeting, 2022.

Talk

• Proceedings of the 42nd International Conference on Machine Learning (ICML), Vancouver, July 2025.
• Workshop on Statistical Network Analysis and Beyond (SNAB), Tokyo, June 2025.
• IMS International Conference on Statistics and Data Science, Nice, December 2024.
• Workshop Honoring Andrew Barron: Forty Years at the Interplay of Information Theory, Probability and Statistical Learning, Yale University, April 2024.
• IMS Asia Pacific Rim Meeting, Melbourne, January 2024.
• Seminar talk, Graduate school of Economics, the University of Tokyo, February 2023.
• IMS International Conference on Statistics and Data Science, Florence, December 2022.
• Workshop on random partition of integers, the University of Tokyo, June 2022.
• Japan Statistical Society Meeting, Keio University, March 2022.

Teaching (PhD level)

• TA: Theory of Probability, fall 2023.
• TA: Stochastic process, spring 2024.
• Instructor: Probability and Stochastic Processes, summer 2024.