Research Group
Deep Models and Optimization

Investigating the interplay between optimizer and architecture in Deep Learning, and new networks for long-range reasoning.

Thumb ticker niki

Niccolò Ajroldi

  • Research Engineer
Thumb ticker img 20190525 wa0024

Destiny Okpekpe

  • Ph. D. Student
Thumb ticker me

Felix Sarnthein

  • Ph. D. Student
Thumb ticker diganta misra

Diganta Misra

  • Ph. D. Student
Thumb ticker 20241125 ellis 238

Niclas Hergenröther

  • Student Assistant
Thumb ticker screenshot 2025 04 10 at 20.31.32

Sajad Movahedi

  • Ph. D. Student
Thumb ticker alexandre

Alexandre François

  • Ph. D. Student
Thumb ticker wenjie fan

Wenjie Fan

  • Ph. D. Student
Thumb ticker albert

Albert Catalán Tatjer

  • Student Assistant
Thumb ticker js

Jaisidh Singh

  • Student Assistant

The purpose of our research is to design new optimizers and neural networks to accelerate technology and scientific discovery with Deep Learning. Our approach is theoretical, with a strong focus on optimization theory as a tool for understanding the challenging dynamics of modern neural networks.
We strongly believe deep learning will revolutionize science and technology, offering solutions to society's most pressing challenges. With a stronger theoretical foundation, we envision a future where scientists and engineers, regardless of their resource limitations, can leverage powerful and reliable deep learning solutions to help make the world a better place.

If you like our mission, please apply for CLS, ELLIS, IMPRS-IS PhD Programs (deadline usually ~Nov 15th).

Teaching at the University of Tübingen: Nonconvex Optimization for Deep Learning (Winter Semester 24/25), Details here.