Beyond classical regimes in statistical inference and machine learning (06/24 --> 12/24)

The current state of the art in Machine Learning (ML) and Statistical Inference heavily relies on principles which defy traditional statistical thinking, such as high overparameterization in deep learning and non-convex optimization on high-dimensional landscapes using stochastic descent. This brings the necessity of investigating previously unexplored statistical regimes where classical results do not apply to better understand these novel and impactful practices. As a result, innovative theoretical approaches have emerged, notably through interdisciplinary collaborations, among which those based on high-dimensional statistics, random matrix theory and mathematical physics figure prominently. This thematic trimester therefore aims at fostering the interaction of researchers from several communities working in this fast-developing and emerging area, as well as providing young researchers and students with opportunities for acquiring knowledge on these new theoretical approaches of ML and statistical inference which will play a major role in the future of these disciplines.

Opening colloquium
An opening colloquium about recent developments and challenges of high-dimensional statistical inference and machine learning.
September, 11th 2024, from 3pm to 5pm (+ cocktail)

Speakers : Lenka Zdeborovà (EPFL, Switzerland) and Andrea Montanari (Stanford U., USA)

More info and registration: link

Thematic school: Optimization & algorithms for high-dimensional machine learning and inference
This thematic school features mini-courses on the study of high-dimensional (random) optimization landscapes, on the dynamics of optimization algorithms in high dimensions, on approximate message passing algorithms, and related topics.
October, 7th to 11th 2024

List of speakers and subjects:
François Malgouyres - Nonconvex optimization landscapes
Edouard Pauwels - Optimization for machine learning
Valentina Ros - Random high-dimensional optimization landscapes
Cynthia Rush - Approximate message passing (AMP) algorithm
(Speaker TBA) - Optimization on overparameterized regimes

More info and registration: link

Thematic school: Models & methods for high-dimensional machine learning and inference
This thematic school features mini-courses on tools and techniques for the analysis of high-dimensional models in statistical inference and machine learning.
October, 14th to 18th 2024

List of speakers and subjects:
Gérard Ben Arous - TBA
Florent Krzakala (to be confirmed) - Replica method
Marc Lelarge - Statistical physics and inference
Alexander S.Wein - Tensor models
Zhenyu Liao - Random matrix theory tools for machine learning and inference

More info and registration: link

Workshop: Recent developments beyond classical regimes in statistical learning
This workshop is focused on recent results on high-dimensional (supervised and unsupervised) machine learning and statistical inference. It will in particular involve a round-table debate with top experts on this domain about the major open problems on the field and some promising trends and recent developments.

*This is a joint workshop with the CIMI Thematic Semester "Stochastic control and learning for complex networks"
November 4th to 8th 2024

List of confirmed speakers (other speakers will soon be announced):
Lenka Zdeborová (EPFL, Switzerland): keynote speaker
Jean Barbier (ICTP, Italy)
Giulio Biroli (ENS, France)
Zhou Fan (Yale U., USA)
Yan Fyodorov (KCL, UK)
Daniel Hsu (Columbia U., USA)
Aukosh Jagannath (Waterloo U., Canada)
Jonathan P. Keating (Oxford U., UK)
Marc Lelarge (ENS, France)
Bruno Loureiro (ENS, France)
Valentina Ros (Paris-Saclay U., France)
Subhabrata Sen (Harvard U., USA)
Pragya Sur (Harvard U., USA)
Christos Thrampoulidis (British Columbia U., Canada)
Pierfrancesco Urbani (IPHT, France)
Yizhe Zhu (California Irvine U., USA)

More info and registration: link

Organisation staff:

Henrique Goulart (IRIT/Toulouse INP)
Vanessa Kientz (CEA List)
Vincent Lahoche (CEA List)
Xiaoyi Mai (IMT/UT2J)
Mohamed Tamaazousti (CEA List)
Matthieu Jonckheere (LAAS), for the workshop

CIMI Thematic Trimester

Institut de Mathématiques de Toulouse (IMT)
Amphithéâtre Laurent Schwartz (building 1R3)
Paul Sabatier University
118 route de Narbonne
Toulouse, France