The past decade brought a revolution to machine learning: algorithms are now able to deal with tasks and amounts of data that seemed to be science fiction only a decade ago. The statistical physics community and the machine learning ones were connected and indeed many concepts and algorithms of machine learning have roots in physics. It is time to revive and strengthen this connection. After a wonderful event in 2018, we gather once again in Cargese in 2023, from July 31st to August 12th, and bring together researchers from machine learning & statistical physics to take full advantage of the strong link between the two fields to make further scientific progress. The program will concentrate on theoretical aspect of machine learning and high-dimensional statistics, and their deep link with physics, as well as the direct applications of machine learning techniques in physics, for instance for sampling and generative problems.

Organisers: Damien Barbier (EPFL, IdePhics Lab.), Vittorio Erba (EPFL, SPOC Lab.), Florent Krzakala (EPFL, IdePhics Lab.), Bruno Loureiro (ENS, Paris), Lenka Zdeborova (EPFL, SPOC Lab.)

Confirmed speakers

Yasaman Bahri (Google)
Gérard Ben Arous (NYU)
Guy Bresler (MIT)
Joan Bruna (NYU)
Ahmed El Alaoui (Cornell)
Marylou Gabrié (Polytechnique Paris)
David Gamarnik (MIT)
Cedric Gerbelot (NYU)
Surbi Goel (UPenn)
Sebastian Goldt (SISSA Trieste)
Alice Guionnet (ENS Lyon)
Suriya Gunasekar (Microsoft)
Boris Hanin (Princeton)
Samuel Hopkins (MIT)
Roberto Imbuzeiro Oliveira (IMPA)
Julia Kempe (NYU)
Yue Lu (Harvard)
Antoine Maillard (ETH Zurich)
Marc Mézard (Bocconi)
Theodor Misiakiewicz (Stanford)
Remi Monasson (ENS Paris)
Cristopher Moore (Santa Fe Institute)
Giogrio Parisi (La Sapienza Roma)
Cengiz Pehlevan (Harvard)
Galen Reeves (Duke)
Cindy Rush (Columbia)
Andrew Saxe (UCL)
Mark Sellke (Harvard)
Guilhem Semerjian (ENS Paris)
Subhabrata Sen (Harvard)
Allan Sly (Princeton)
Haim Sompolinsky (Harvard & HUJI)
Nathan Srebro (TTIC)
Pragya Sur (Harvard)
Eric Vanden-Eijnden (NYU)
Soledad Villar (Johns Hopkins)
Matthieu Wyart (EPFL)
Ilias Zadik (MIT)
Riccardo Zecchina (Bocconi)

Last updated on 02/02/2023


To apply, please fill the online form clicking the Apply now button below.

The deadline for application is March, 31st 2023.

The selection of the participants will take place in the days following the deadline.

Practical informations

The school and workshop cost is 1100 euros per participant, covering accommodation, lunches and breakfasts.

While participant can arrive on 31/7 and leave on 12/8, the conference will take place between 1/8 and 11/8.

More information can be found on the institute webpage.

The poster of the event can be downloaded here


For any question, write

Feel free to tweet about the school!



drawingdrawingdrawingdrawing drawing drawing