Statistical Safeguarding Workshop 2026
Statistical Safeguarding Workshop 2026
Date: April 9, 2026 (JST)
Format: Hybrid (In-person + Online)
Venue: RIKEN AIP Nihonbashi Open Space
- Open Space is available to AIP researchers and invited guests.
Hosted by RIKEN AIP Imperfect Information Learning Team & The University of Tokyo
URL of the workshop webpage: https://statsafe.github.io/workshop.html
Overview
In recent years, the social deployment of AI and machine learning has been accelerating. At the same time, the importance of “safeguarding” - addressing societal requirements such as privacy protection, the validity of statistical inference, robustness and safety, and explainability - has become increasingly critical.
This workshop aims to examine these challenges from the perspectives of statistics and machine learning. By sharing insights from cutting-edge research, participants will engage in discussions that also consider practical applications.
Program
Morning Session
09:30 – 09:35 Greeting from JST ASPIRE
Miyano Kenjiro (Program Director, ASPIRE, JST)
09:35 – 09:40 Welcome & Opening Remarks
Masashi Sugiyama (RIKEN) & Takashi Ishida (UTokyo)
09:40 – 10:10 Takashi Ishida (The University of Tokyo / RIKEN AIP)
Reliable Model Evaluation Without Full Ground Truth
10:10 – 10:40 Yi Yu (University of Warwick)
Optimal Federated Learning under Differential Privacy Constraints
10:40 – 11:10 Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
Recent Advances in Learning from Imperfect Information: Weak Supervision, Distribution Shift, and Reward Modeling
11:10 – 11:40 Coffee Break & Poster Session
11:40 – 12:10 Matt Thorpe (University of Warwick)
Discrete-To-Continuum Limits in Graph-Based Semi-Supervised Learning
12:10 – 12:40 Giovanni Montana (University of Warwick)
TBA
12:40 – 12:45 ASPIRE Program Introduction from JST
12:45 – 13:50 Lunch Meeting
Afternoon Session
13:50 – 14:20 Takeru Matsuda (The University of Tokyo)
Empirical Bayes 1-bit Matrix Completion (tentative)
14:20 – 14:50 Michael Gutmann (The University of Edinburgh)
Bayesian Inference and Design
14:50 – 15:20 Coffee Break & Poster Session
15:20 – 15:50 Wenkai Xu (University of Warwick)
TBA
15:50 – 16:20 Takayuki Osa (RIKEN AIP)
Efficient and Robust Robot Learning for Safe Robotic Systems
16:20 – 16:50 Coffee Break & Poster Session
16:50 – 17:20 Futoshi Futami (The University of Osaka / RIKEN AIP)
TBA
17:20 – 17:50 Gesine Reinert (University of Oxford) Online talk
Synthetic Networks
17:50 – 18:05 Closing Remarks & Discussion
Wenkai Xu
