Hello! I’m Hiro.
Hirofumi Shiba (Hiro) is a Ph.D. student supervised by Kengo Kamatani at the Institute of Statistical Mathematics (ISM), Tokyo, Japan.
My research focuses on deepening our understanding of learning algorithms through the lens of their (scaling / continuous-time) limit dynamics. From these perspectives, algorithms reveal their intrinsic properties, and my work aims to provide a unified understanding of various algorithms under a common mathematical framework, i.e., flows on the space of probability measures.
Qualifications
Ph.D. in Statistical Science, 2028 (expected)
Graduate University for Advanced Studies, SOKENDAI, Japan
B.Sc. in Mathematics, 2023
University of Tokyo, Japan
Activities
Data Scientist, 2023.4 – present
PreMedica Inc., Tokyo, Japan
Consulting in the field of medical data analysis.
Research Fellow, 2025.4 – present
Graduate University for Advanced Studies, SOKENDAI, Japan
Supported by JST BOOST, Japan Grant Number JPMJBS2412.
Research Visits
Ulm University, Germany, 2025.7.13–26
Evgeny Spodarev at the Institute of Stochastics.
National University of Singapore, 2025.6.1–30
Alexandre Thiéry at the Department of Statistics & Data Science.
University College London, UK, 2024.11.4–12.2
Alexandros Beskos at the Department of Statistical Science.
Awards
Best Poster Award, 2025.3
19th Spring Meeting of the Japanese Statistical Society
Director’s Award, 2025.3
Japanese Statistical Society Certificate
Languages
Japanese (native), English (fluent), Mandarin Chinese (fluent), German (basic), Korean (basic)