Vortrag von Dr. Claire Vernade

Dr. Claire Vernade
University of Tübingen
Tübingen, Germany

Tuesday 2024-07-02 4 p.m.
IST Seminar Room 2.255 - Pfaffenwaldring 9 - Campus Stuttgart-Vaihingen

Abstract

Discovery in Science is a complex process that involves exploration and planning, as well as hypothesis testing. In this talk, I will discuss why I believe that Reinforcement Learning can be an important ingredient in Machine Learning for Science. I will present 2 recent works I have been working on with my group: 

• A Pontryagin's perspective on Open-Loop Reinforcement Learning:   https://arxiv.org/abs/2405.18100 (w/ Onno Eberhard and Michael Mühlebach)
• Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits: https://arxiv.org/abs/2402.05878 (with Nicolas Nguyen, Imad Aouali, Andras György)

The talk will start with a gentle introduction to Reinforcement Learning Theory.

Biographical Information

Claire is a Group Leader at the University of Tuebingen, in the  Cluster of Excellence Machine Learning for Science(*). She was awarded an  Emmy Noether award under the AI Initiative call in 2022. 
Her research is on sequential decision making. It mostly spans bandit problems, and theoretical Reinforcement Learning, but her research interests extend to Learning Theory and principled learning algorithms. Her goal is to make Machine Learning a continual process whose dynamical aspects are understood and controlled. 
Between November 2018 and December 2022, she was a Research Scientist at DeepMind in London UK in the Foundations team lead by  Prof. Csaba Szepesvari. She did a post-doc in 2018 with  Prof. Alexandra Carpentier at the University of Magdeburg in Germany while working part-time as an Applied Scientist at Amazon in Berlin. She received her PhD from Telecom ParisTech in October 2017, under the guidance of  Prof. Olivier Cappé. 
I am co-leading the  Women in Learning Theory initiative as well as the new group of  Tübingen Women in Machine Learning, please reach out if you have questions or if you'd like to help.