 | Monter d'un niveau |
Raynaud, P. (2024). Exploiting the Partially-Separable Structure in Quasi-Newton Methods for Unconstrained Optimization and Deep Learning [Thèse de doctorat, Polytechnique Montréal]. Accès restreint
Rahbarnia, F., & Raynaud, P. (2023). FluxNLPModels.jl and KnetNLPModels.jl : connecting deep learning models with optimization solvers. (Non spécifié). Lien externe
Raynaud, P., Orban, D., & Bigeon, J. (2023). PLSR1 : a limited-memory partioned quasi-Newton optimizer for partially-separable loss functions. (Rapport technique n° G-2023-41). Lien externe
Raynaud, P., & Orban, D. (septembre 2023). Limited-memory stochastic partitioned quasi-newton training [Affiche]. Edge Intelligence Workshop, Montreal, Qc, Canada (1 page). Lien externe
