Our core research lies at the intersection between optimization and machine learning.  This includes using optimization to deepen our understanding of deep learning models, as well as designing and analyzing new optimization methods, with a special interest  for applications in the field of machine learning.

Openings

Our group has several PhD students and Post-doc openings in the areas of optimization and deep learning theory. Potential research topics include the development of adaptive optimization methods, the exploration of the loss landscape in deep neural networks, and the design of novel neural network architectures that enhance efficiency in both training and inference.

PhD applicants must possess a Master’s degree in mathematics, theoretical physics, or computer science with a strong theoretical focus. Post-doctoral applicants should have completed a PhD in these or related fields.

If interested, please send an application as described below to aurelien.lucchi (at) unibas.ch.

Your application should be a **single pdf file** containing the following files:

• Short motivation statement (maximum 150 words) explaining your interest in the position and justifying why your background is a good fit for the position
• Curriculum vitae (including a list of publications if applicable) 
• Scanned transcripts of bachelor's and master’s degree
• Contact info (no direct recommendation letters) for peers who can recommend you
• Your latest thesis (and/or one of your publications if applicable)