Welcome! I am a post-doctoral researcher at the Institut de Physique Théorique in Paris, where I work on problems at the interface of statistical physics and information processing in the group of Lenka Zdeborová.
Videos & news coverage
- I recently had the chance to talk about our recent work on the dynamics and the performance of neural networks at a workshop on Theoretical Physics For Deep Learning at this year’s ICML. Here’s a link to the video:
- Watch the video abstract for our recent article in the New Journal of Physics on the thermodynamic efficiency of learning a rule with neural networks:
Click to play!
- Or have a look at a short news article on Phys.org about our PRL on the stochastic thermodynamics of Learning.
I am interested in understanding how to process large amounts of information efficiently.
One focus of my research is understanding what makes information processing in living organisms so efficient — after all, a human brain might not be behind the best Go player in the world anymore, but it still beats any supercomputer in terms of power consumption and efficiency by a few orders of magnitude.
Another theme of my work is to tackle challenging problems in learning and inference by turning concepts from the statistical physics of complex systems into algorithms.
- 03/2019 – 04/2019: Visiting researcher at the Kavli Institute for Theoretical Physics (KITP), participating in the program Machine Learning for Quantum Many-Body Physics
- 02/2018 – 05/2018: Visiting researcher with Lenka Zdeborová in the lab of Prof. Patrick Charbonneau at Duke University, NC, USA.
- since 11/2017: Postdoctoral research associate with Dr. Lenka Zdeborová at the Institut de Physique Théorique in Paris.
- 2014-2017: PhD student under the supervision of Prof. Udo Seifert at the II. Institut für Theoretische Physik, University of Stuttgart.
- 2010-2014: B.A., M.Sci. in Experimental and Theoretical Physics, University of Cambridge, UK.
- 2009: Abitur, Schule Schloss Salem, Germany.