Showing 2026 · cs.LGShow all
2 papers · 2 filters
cs.LG2026
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…
cs.LG2026
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…