We are organizing a two days virtual conference on “robustness and privacy” on March 22 and March 23, 2021.
The registration is free but mandatory; a Zoom link will be sent to all participants a day before the conference
Each talk will be 25 minutes long followed by a 5 minutes dicussion for questions. The conference should start on Monday 22th of March and Tuesday 23rd of March at 16:30 up to 19h30 (Paris local time).
Support The conference is suported by the mathematical institute of CNRS and the Médiamétrie Chair.
Some words about the conference:
Robustness has been studied a lot in statistics since the seminal work of Huber. Many algorithms have also been designed in Machine Learning. However, this subject has witnessed an important renew during the last 10 years both in the statistical and computer science communities. It involves statistics, optimization, probability and machine learning as mathematical domains.
In the meantime, privacy has received a lot of attention in the Computer science community because it is a central issue for the security of many sensitive data in finance, economics, administration and, more basically, for keeping customers’ trust in trading. It seems however possible to randomize data in order to ensure a controlled amount of privacy of the individuals while still being able to learn some patterns out of it: this is the cornerstone of privacy. Only recently, statisticians started to analyze privacy mechanisms. In particular, they discovered several interesting common features between robustness issues and privacy. That is the main motivation on our side to organize a joint conference simultaneously on the two subjects.
Organization commitee: Cristina Butucea, Victor-Emmanuel Brunel, Nicolas Chopin, Arnak Dalalyan, Guillaume Lecué, Matthieu Lerasle, Vianney Perchet and Alexandre Tsybakov.
Info contact You can email me for more information.