M11. Inverse Problems in Statistics

Inverse problems arise naturally in statistical inference, where the goal is to recover unknown parameters or latent structures from indirect, noisy, or incomplete observations. This minisymposium will explore methodological and theoretical advances at the interface of inverse problems and statistics, with a focus on regularization techniques, Bayesian approaches, and data-driven methods. Applications span signal and image processing, machine learning, and uncertainty quantification. Special attention will be given to challenges related to ill-posedness, robustness, and computational efficiency.

The minisymposium will bring together researchers working on both foundational aspects and real-world applications, fostering discussions on new directions and interdisciplinary collaborations.

Organizer:
Pierre Maréchal, Institut de Mathématiques de Toulouse, Université of Toulouse, France, This email address is being protected from spambots. You need JavaScript enabled to view it.

Invited Speakers:
Valérie GIRARDIN, Université de Caen Normandie, France
Minimum of divergences with relaxation: alternative approaches to duality

Clément Marteau, Université Lyon I - Claude Bernard, France, This email address is being protected from spambots. You need JavaScript enabled to view it.
A non-asymptotic upper bound in prediction for the Partial Least Square estimator

Thanh Mai PHAM NGOC, Universite Sorbonne Paris Nord, France, This email address is being protected from spambots. You need JavaScript enabled to view it.
Nonparametric estimation of the fragmentation kernel based on a partial differential equation stationary distribution approximation

Anne Vanhems, Toulouse Business School, France, This email address is being protected from spambots. You need JavaScript enabled to view it.
Random coefficients regressions and Radon transform inversion