The JSTAR 2026 Conference will take place at ENSAI on March 19-20, 2026.
This edition will focus on Functional Data Analysis.
Invited talks will cover several related topics, including dimension reduction, functional data objects, panel data, testing for functional data, and estimation for functional data.
JSTAR 2026 : 20th Statistics Days at Rennes
Since 2004, statistics research teams in the Rennes region have organised the annual Rennes Statistics Days (JSTAR or Journées de STAtistique de Rennes).
This year, ENSAI is organising the 20th edition in partnership with ANR FUNMathStat. The event will bring together statisticians from Rennes to discuss recent developments in functional data analysis.
The conference will take place over two days, on Thursday 19 and Friday 20 March 2026, and will feature presentations by invited speakers. A dinner will be held on Thursday evening at the Taverne de la Marine (2 Pl. de Bretagne, 35000 Rennes).
The conference is open to all. Registration is free but compulsory, with a deadline of 15 February 2026.
For more information, please refer to the dedicated JSTAR website: JSTAR2026 : Journées de STAtistique de Rennes – 20ème édition – Sciencesconf.org
Perry De Valpine (UC Berkeley)
Statistics-ENSAI Seminar : Every Friday
Time:
Date: October 17, 2025
Room :
Perry De Valpine, UC Berkeley
Abstract :
Organizers:
Marie-Pierre Etienne
Sponsors:
CREST-ENSAI
Futoshi Furami (Osaka University) “Uncertainty Quantification through Calibration in Classification Problems”
Futoshi FURAMI – https://sites.google.com/view/futoshifutami/home (invité de Ikko Yamane)
Le vendredi 12 septembre 2025
de 11h à 12h (café d’accueil à partir de 10h40)
à l’ENSAI, Campus de Ker Lann à Bruz – salle 10
Title :Uncertainty Quantification through Calibration in Classification Problems
Abstract:In recent years, in high-risk domains such as medical diagnosis, weather forecasting, and financial risk management, there has been a strong demand for the reliability of probabilities output by machine learning models. A representative measure for assessing this reliability is calibration, which evaluates the degree of agreement between predicted probabilities and the actual frequency of events. However, it has been reported that modern deep learning models often exhibit poor calibration, and improving this issue has become an urgent challenge.
In this talk, I will introduce basic ideas related to calibration, as well as our recent research, including generalization error analysis of calibration errors based on statistical learning theory, and correction algorithms utilizing PAC-Bayesian methods.
Lin Tian (INSEAD)
Organized by ENSAI’s Economics Department, enable guest researchers to present their work. They are open to the public and subject to registration.
June 13, 2025, 11am-12.15pm: Lin Tian (INSEAD)
Robert Miller (Carnegie Mellon University)
Organized by ENSAI’s Economics Department, enable guest researchers to present their work. They are open to the public and subject to registration.
May 13, 2025, 11am-12.15pm: Robert Miller (Carnegie Mellon University)
Xiaoyun Yu (Shanghai Advanced Institute of Finance)
Organized by ENSAI’s Economics Department, enable guest researchers to present their work. They are open to the public and subject to registration.
May 7, 2025, 11am-12.15pm: Xiaoyun Yu (Shanghai Advanced Institute of Finance)
Camille Hémet (Université Paris 1 Panthéon-Sorbonne / Paris School of Economics)
Organized by ENSAI’s Economics Department, enable guest researchers to present their work. They are open to the public and subject to registration.
March 14, 2024, 11am-12.15pm: Camille Hémet (Université Paris 1 Panthéon-Sorbonne / Paris School of Economics)
Anthony Terriau (Le Mans University)
Organized by ENSAI’s Economics Department, enable guest researchers to present their work. They are open to the public and subject to registration.
December 13, 2024, 11am-12.15pm: Anthony Terriau (Le Mans University)
Felipe Saffie (University of Virginia)
Organized by ENSAI’s Economics Department, enable guest researchers to present their work. They are open to the public and subject to registration.
December 6, 2024, 11am-12.15pm: Felipe Saffie (University of Virginia)