1 code implementation • 14 Jun 2022 • Dounia Lakhmiri, Dominique Orban, Andrea Lodi
We consider the problem of training a deep neural network with nonsmooth regularization to retrieve a sparse and efficient sub-structure.
no code implementations • 29 Nov 2021 • Sanae Lotfi, Tiphaine Bonniot de Ruisselet, Dominique Orban, Andrea Lodi
In this paper, we consider both first- and second-order techniques to address continuous optimization problems arising in machine learning.
no code implementations • 6 Jan 2021 • Ding Ma, Dominique Orban, Michael A. Saunders
We give numerical results from a Julia implementation of Algorithm NCL on tax policy models that do not satisfy the LICQ, and on nonlinear least-squares problems and general problems from the CUTEst test set.
Optimization and Control Numerical Analysis Numerical Analysis
no code implementations • 10 Dec 2020 • Sanae Lotfi, Tiphaine Bonniot de Ruisselet, Dominique Orban, Andrea Lodi
We propose a new stochastic variance-reduced damped L-BFGS algorithm, where we leverage estimates of bounds on the largest and smallest eigenvalues of the Hessian approximation to balance its quality and conditioning.
1 code implementation • 7 Oct 2019 • Daniela di Serafino, Dominique Orban
We consider the iterative solution of regularized saddle-point systems.
Numerical Analysis Numerical Analysis 65F08, 65F10, 65F50, 90C20