Thumb ticker lg me

Felix Sarnthein

PhD Student

Felix is a doctoral candidate at the Max Planck ETH Center for Learning Systems (CLS) under the joint supervision of Dr. Antonio Orvieto (ELLIS Institute) and Prof. Thomas Hofmann (ETH Zurich). After obtaining his MSc in Computer Science from ETH Zurich, he visited Prof. Thomas Hofmann (ETH Zurich) and Prof. Nicolas Flammarion (EPFL Lausanne) as a research assistant.

Felix is generally fascinated by the learning dynamics of neural networks. What are the minimal required conditions for a system to learn? And can we use such insights to design more efficient training methods? He aims to investigate such questions at the intersection of empirical and theoretical research of deep learning. This involves, in particular, self-supervised learning, knowledge distillation, the interplay of optimization methods and deep networks, as well as long-range and hierarchical feature learning of sequential data. He believes that understanding such topics will lead to better-informed and potentially more efficient training methods and architectures in the long term.

Google Scholar: