معرفی
Claire Vernade is a Group Leader at the University of Tübingen within the Cluster of Excellence Machine Learning for Science. Her research focuses on sequential decision making and theoretical reinforcement learning (RL), particularly in non-stationary environments, bandit problems, and principled learning algorithms. She has received prestigious awards including the Emmy Noether Award (2022) and an ERC Starting Grant (2024) for her projects FoLiReL and ConSequentIAL, respectively. Claire has previously worked as a Research Scientist at DeepMind (London) and as a part-time Applied Scientist at Amazon (Berlin).
- Education: PhD in Machine Learning from Telecom ParisTech (2017), under Prof. Olivier Cappé.
Research Interests include:
- Sequential Decision Making
- Bandit Problems (Combinatorial, Delayed Feedback, Sparse Actions)
- Reinforcement Learning Theory
- Meta-Learning and Lifelong Learning
- Optimization Algorithms
- Game-Theoretic Approaches to PCA
Publications highlight trends in non-stationary environments, contextual bandits, and theoretical foundations of RL and bandit algorithms. Her work spans applications in scientific discovery, statistical testing, and optimization.
Scientific Awards:
- Emmy Noether Award (2022)
- ERC Starting Grant (2024)
- Outstanding Paper Award at ICLR 2021
Advising and Grants: Claire leads a research group with ongoing PhD and postdoc opportunities through IMPRS-IS and ELLIS doctoral programs. Her projects receive funding from the European Research Council and DFG, with focus on continual learning and adaptive AI systems.
Labs/Teams: She coordinates the Tübingen Women in Machine Learning (TWiML) initiative and co-leads the Women in Learning Theory (WiML-T) website. Her group emphasizes diversity, inclusivity, and collaborative research in theoretical machine learning.
