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

Master Thesis Student
Thumb ticker me

Felix Sarnthein

PhD Student
Thumb ticker profile siyi

Si Yi Meng

PhD Research Intern
Thumb ticker ph

Vera Milovanovic

Master Thesis Student / RA
Thumb ticker diganta misra

Diganta Misra

PhD Student
Thumb ticker screenshot 2024 10 19 at 01.27.50

Carlos Santillán

Research Intern
no image

Niclas Hergenröther

Hiwi Research Assistant
Thumb ticker omar

Omar Coser

PhD Research Intern
no image

Sajad Movahedi

PhD Student
no image

Alexandre François

INRIA PhD Student
Thumb ticker wenjie fan

Wenjie Fan

PhD Student

The purpose of our research is to design new optimizers and neural networks to accelerate scientific discovery through efficient and reliable training. 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 Nov 15th).

If you're a young scientist (e.g. bachelor or master student) facing societal, financial, or personal challenges, we would love to contribute to your development by offering you a fully-funded 3-month project! Please apply to the CaCTüS Internship.