Home

About me

I am a researcher working on Optimization for Machine Learning. Since September 2024, I am a postdoc at Inria Paris, advised by Francis Bach, Umut Simsekli, and Adrien Taylor. Previously, I obtained my PhD at the Technical University of Munich (TUM), supervised by Professor Michael Ulbrich.

Research Overview. A common theme of my past work is to understand, simplify, and ultimately improve training recipes for ML models. As a result, my research is often trying to bridge optimization theory and machine learning practice.

Selection of recent works:

• Understanding the behaviour of learning-rate schedules for LLM training [ICML 2025]
• What are good optimizers for training diffusion models? [EurIPS 2025]
• Developing training algorithms that need less tuning (MoMo [ICML 2024] and a proximal Polyak step size [TMLR 2023])

Contact

You can write me at firsstname[dot]lastname[at]tum[dot]de.

News

• [December 2025] I will be at EurIPS in Copenhagen.
• [July 2025] I will be at ICML in Vancouver.
• [September 2024] Moved to Paris.
• [July 2024] I successfully defended my PhD thesis!
• [August 2023] Visiting researcher at CCM, Flatiron Institute, New York City.
• [August 2022] Visiting researcher at CCM, Flatiron Institute, New York City.