About
I am a PhD student in machine learning at the University of Tübingen and the International Max Planck Research School for Intelligent Systems (IMPRS-IS) where I work under the supervision of Robert Bamler. My research focuses on the interface between deep learning and probabilistic modeling. Specifically, I am interested in developing deep learning models that can reliably estimate the uncertainty of their predictions as well as algorithms that use uncertainty to make decisions. Overall, my goal is to contribute to the development of Bayesian deep learning by improving priors and inference techniques.
Education
Prior to the University of Tübingen, I did a Bachelor’s degree in Communication Systems at EPFL and a Master’s degree in Computer Science at ETH Zürich. In the conext of my master thesis, I worked with Vincent Fortuin, Alexander Immer, Max Horn and Gunnar Rätsch from ETH Zurich on applying Bayesian inference to the transformer model. Before starting my PhD, I worked at Amazon as an applied research intern where I worked with Artur Bekasov and Tammo Rukat on uncertainty modeling in gradient boosting machines with applications to bandits.
Contact
email: tristan.cinquin@uni-tuebingen.de
Cluster of Excellence “Machine Learning”
Maria-von-Linden-Str. 6
72076 Tübingen