| PLSR1: A limited-memory partitioned quasi-Newton op-timizer for partially-separable loss functions P Raynaud, D Orban, J Bigeon Les Cahiers du GERAD ISSN 711, 2440, 2023 | 1 | 2023 |
| Partially-separable loss to parallellize partitioned neural network training P Raynaud, D Orban, J Bigeon Les Cahiers du GERAD ISSN 711, 2440, 2023 | 1 | 2023 |
| A framework around limited-memory partitioned quasi-Newton methods J Bigeon, D Orban, P Raynaud Les Cahiers du GERAD ISSN 711, 2440, 2023 | 1 | 2023 |
| L'exploitation de la structure partiellement-séparable dans les méthodes quasi-Newton pour l'optimisation sans contrainte et l'apprentissage profond P Raynaud Université Grenoble Alpes [2020-....]; Polytechnique Montréal (Québec, Canada), 2024 | | 2024 |
| Exploiting the Partially-Separable Structure in Quasi-Newton Methods for Unconstrained Optimization and Deep Learning P Raynaud Polytechnique Montréal, 2024 | | 2024 |
| FluxNLPModels. jl and KnetNLPModels. jl: connect F Rahbarnia, P Raynaud Les Cahiers du GERAD ISSN 711, 2440, 2023 | | 2023 |
| PartiallySeparableNLPModels. jl: A Julia framework for partitioned quasi-Newton optimization J Bigeon, D Orban, P Raynaud JOPT 2023, 2023 | | 2023 |
| Limited-memory stochastic partitioned quasi-newton training P Raynaud, D Orban Edge Intelligence Workshop 2022, 2022 | | 2022 |
| Exploiting the partially separable structure in quasi-Newton optimization J Bigeon, D Orban, P Raynaud JOPT 2022, 2022 | | 2022 |
