19 citations
- Centre de Recherche en Mathématiques de la DécisionFR17 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Université Paris Sciences et LettresFR5 papers
- École Normale Supérieure - PSLFR3 papers
- Sorbonne UniversitéFR3 papers
- AGH University of KrakowPL2 papers
- Département de mathématiques et applicationsFR2 papers
- LamsadeFR2 papers
- AgroParisTechFR1 paper
- Aix-Marseille UniversitéFR1 paper
- Ariel UniversityIL1 paper
- Atlantic General HospitalUS1 paper
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Robustness Cannot be Reduced to Regularization: Studying Adversarial Training Beyond the Linear Case
David A. R. Robin, Rafael Pinot, Yann Chevaleyre
The vulnerability of ML models to adversarial examples has recently emerged as a major concern. While adversarial training is one of the most effective countermeasures to this issu…
cs.LG2025
Forward Only Learning for Orthogonal Neural Networks of any Depth
Paul Caillon, Alex Colagrande, Erwan Fagnou +2
Backpropagation is still the de facto algorithm used today to train neural networks. With the exponential growth of recent architectures, the computational cost of this algorithm a…