8 papers
Muon Is Theoretically Wrong For Convolutions, But Empirically Effective
Thibaut Boissin, Thomas Massena, Mathieu Serrurier +1
Muon, an optimizer known for its efficiency, has a clear interpretation for matrix-valued updates, but convolutional kernels are stored as four-dimensional tensors. Standard implem…
LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks
Arthur Chiron, Franck Mamalet, Thomas Massena +2
While accuracy, robustness, and calibration are all essential for reliable neural networks, they are often studied separately; developing models that satisfy all three simultaneous…
From SGD to Muon: Adaptive Optimization via Schatten-p Norms
Thomas Massena, Corentin Friedrich, Mathieu Serrurier
Modern optimizers, like Muon, impose matrix-wise geometry constraints on their updates. These matrix-wise constraints can be unified under Linear Minimization Oracle (LMO) theory.…
Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks
Thibaut Boissin, Franck Mamalet, Valentin Lafargue +1
Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generativ…
Fast and Flexible Robustness Certificates for Semantic Segmentation
Thomas Massena, Corentin Friedrich, Franck Mamalet +1
Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust De…
Turbo-Muon: Almost-Orthogonal Pre-Conditioning for Fast Muon Updates
Thibaut Boissin, Thomas Massena, Franck Mamalet +1
Orthogonality-based optimizers, such as Muon, have recently shown strong performance across large-scale training and community-driven efficiency challenges. However, these methods…
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
Thomas Massena, Léo andéol, Thibaut Boissin +4
Conformal Prediction (CP) has proven to be an effective post-hoc method for improving the trustworthiness of neural networks by providing prediction sets with finite-sample guarant…
An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures
Thibaut Boissin, Franck Mamalet, Thomas Fel +3
Orthogonal convolutional layers are valuable components in multiple areas of machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitz-constrained mo…