About me
I am currently working as a postdoctoral researcher in Deep Learning Theory team at RIKEN AIP.
Research Interests
- Bayesian statistics
- Spatio-temporal modelling
- Statistical learning theory for large-scale model
Recent Papers
Preprint
Wakayama, T., and Banerjee, S. (2024), “Process-based Inference for Spatial Energetics Using Bayesian Predictive Stacking”. arXiv preprint, arXiv:2405.09906, code.
Wakayama, T. and Sugasawa, S. (2024), “Ensemble Prediction via Covariate-dependent Stacking”. arXiv preprint, arXiv:2408.09755, code.
Wakayama, T. (2024), “Bayesian Inference for Consistent Predictions in Overparameterized Nonlinear Regression”. arXiv preprint, arXiv:2404.04498, code.
Publication
Wakayama, T. and Sugasawa, S. (2024), “Spatiotemporal Factor Models for Functional Data with Application to Population Map Forecast”. Spatial Statistics. (publication, code)
Wakayama, T. and Sugasawa, S. (2024), “Functional Horseshoe Smoothing for Functional Trend Estimation”. Statistica Sinica. (publication)
Wakayama, T. and Imaizumi, M. (2024), “Fast Convergence on Perfect Classification for Functional Data”. Statistica Sinica. (publication)
Recent Talks
Wakayama, T., Sugasawa, S., Kobayashi, G. “Similarity-based Random Partition Distribution for Clustering Functional Data”, ISBA World Meeting 2024, Venice, Italy, June 2024.
Wakayama, T., Sugasawa, S. Spatiotemporal factor models for functional data with application to population map forecast, EcoSta2023, Tokyo, Japan, August 2nd, 2023.
Wakayama, T. Spatio temporal factor models for large scale data, 64th ISI World Statistics Congress, Ottawa, Canada, July 17th, 2023.
Recent Awards & Grants
2023/10-2025/3 ACT-X「次世代AIを築く数理・情報科学の革新」, JST.
2023 ISI東京大会記念奨励賞, 日本統計学会
2022/04- 日本学術振興会特別研究員DC1, JSPS.
Education
Ph.D. in Economics, The University of Tokyo, 2025
Dissertation: “Nonparametric Bayesian Statistics for High-dimensional Data”
Supervisor: Masaaki Imaizumi
M.S. in Economics, The University of Tokyo, 2022
Master’s Thesis: “Trend Filtering for Functional Data: Optimization and Bayesian Approach”
Supervisor: Shonosuke Sugasawa
B.S. in Engineering, Osaka Prefecture University, 2020