Ayoub Ajarra

I’m a final year PhD candidate at Inria in Scool team (previously SequeL) under the supervision of Debabrota Basu and Philippe Preux. Prior to my PhD, I was a visiting research student at MILA, supervised by Yoshua Bengio, Loubna Benabbou and Dianbo Liu.

My research investigates the theoretical foundations of machine learning, which underpin the success of modern AI systems. My current work focuses on developing frameworks that enable policymakers to detect and assess algorithmic bias in realistic settings, particularly in dynamic and competitive markets where companies continuously adapt their systems throughout the audit process. In parallel, I study fundamental questions in learning theory including compression schemes, and more recently, I have been working on large language models.