https://wasp-sweden.org/wallenberg-advanced-scientific-forum-autumn-2026
Talk @Workshop on Learning-based Methods for Inverse Problems 2026, ENS de Lyon, Sept 14 2026
on Training dynamics of ReLU Networks: a Path-lifting Perspective
Minisymposium “Mathematical aspects of deep learning” @ Curves & Surfaces 2026, St-Malo, June 8-12 2026
https://cs2026.sciencesconf.org
At the occasion of the 2026 edition of the Curves and Surfaces conference, held in the nice city of St-Malo, I am organizing a minisymposium on Mathematical aspects of deep learning.
Speakers:
- Laura Balzano, Hardware-Aware Structured Attention with Monarch Matrices
- Etienne Boursier, Incremental Learning in two-layer ReLU networks
- Claire Boyer, Attention-based clustering,
- Kathlén Kohn, Algebraic Neural Networks: Identifiability, Singularities, Critical Points
- François Malgouyres, Geometry-induced Regularization in Deep ReLU Neural Networks
- Holger Rauhut, The implicit bias phenomenon in deep learning
SHARP+Foundry workshop @COLT 2025 in Lyon, June 30th 2025
On June 30th 2025, at ENS de Lyon, in the framework of the COLT2025 conference on learning theory, the SHARP and Foundry projects of the PEPR IA are co-organizing a one-day workshop on “Frugal and Robust Foundations for Machine Learning – Occam’s razor at the age of LLM’s”. The workshop will be dedicated to recent advances in frugal and robust learning. Details here