News & Updates Archive

Our paper On the existence of consistent adversarial attacks in high-dimensional linear classification has been accepted as a Spotlight at ICML 2026.

Our paper with Nikolaos Tsilivis, Bruno Loureiro, and Julia Kempe has been accepted to Transactions on Machine Learning Research (TMLR).

Excited to help organize the third edition of the Lausanne Event on Machine Learning and Neural Network Theory (LemanTH), from April 20–24, 2026 at the Bernoulli Center (EPFL), together with Florent Krzakala and Bruno Loureiro.

I will see you at AISTAT2025 in beautiful Phuket, Thailand. I will present our work titled “A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-offs”.

For the next two weeks I will attend the Winter School Towards a theory for typical-case algorithmic hardness in the beautiful Les Houches, France.

Next week I will be attending the Statistical Physics of Deep Learning school in Como, Italy. I will present our work “A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-offs” during the poster session. I can’t wait to follow the lectures from Francesca Mastrogiuseppe and Mathieu Wyart!

I will see you at AISTAT2024 in Valencia, Spain. I will present our work on “Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers”.

For the next week I will be visiting the Data Science Center at Ecole Normale Supérieure in Paris. I am happy to talk if you are around!

I am looking forward to spend two weeks in Cargese, Corsica for the Statistical Physics and Machine Learning Back Together Again. Hope to meet you there!