| Time: | July 2, 2024 |
|---|---|
| Download as iCal: |
|
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.