Paul Raynaud
BackPublications
Cahiers du GERAD
Sep 2023
G-2023-41
PLSR1: A limited-memory partitioned quasi-Newton optimizer for partially-separable loss functions
PLSR1: A limited-memory partitioned quasi-Newton optimizer for partially-separable loss functions
Improving neural network optimizer convergence speed is a long-standing priority. Recently, there has been a focus on quasi-Newton optimization methods, whi...
BibTeX reference
Aug 2023
Historically, the training of deep artificial neural networks has relied on parallel computing to achieve practical effectiveness. However, with the increas...
BibTeX reference
Jul 2023
G-2023-25
FluxNLPModels.jl and KnetNLPModels.jl: Connecting deep learning models with optimization solvers
FluxNLPModels.jl and KnetNLPModels.jl: Connecting deep learning models with optimization solvers
Farhad Rahbarnia and Paul Raynaud
This paper presents <code>FluxNLPModels.jl</code> and <code>KnetNLPModels.jl</code>, new Julia packages enabling a neural network, modelled with either Flux....
BibTeX reference
May 2023
We present a Julia framework dedicated to partially-separable problems whose element function are detected automatically. This framework takes advantage of ...
BibTeX reference