Geometry of Tensors and Neural Networks 2026

About the Workshop

This one-day workshop will focus on the theoretical study of neural networks and tensor decompositions using geometric tools. The main topic is the geometry of the corresponding algebraic varieties: neurovarieties (in case of neural networks) and secant varieties (for tensor decompositions). In machine learning theory, understanding geometry of neurovarieties has proven to be the key to reveal many of their fundamental properties such as their identifiability, expressivity, and the behavior of optimization algorithms (see, for example, neuroalgebraicgeometry.ai ). The workhop will present recent developments and discuss connections between neural networks and tensor decompositions.

This is a follow-up of the workshop on geometry of tensors organized in 2025.

Registration

Registration is free but mandatory (before May 21) (registration link) You are welcome to propose a short talk or poster presentation.

Invited speakers

• Kathlén Kohn (KTH, Stockholm, Sweden)
• Alex Massarenti (University of Ferrara, Ferrara, Italy)
• Maksym Zubkov (University of British Columbia, Vancouver, Canada)

Preliminary schedule

Organizers

• Ricardo Borsoi
• Marianne Clausel
• Konstantin Usevich
• SiMul research group of CRAN

Contact: firstname.lastname @ univ-lorraine.fr