This paper addresses risk averse constrained optimization problems where the objective and constraint functions can only be computed by a blackbox subject to...
Improving neural network optimizer convergence speed is a long-standing priority.
Recently, there has been a focus on quasi-Newton optimization methods, whi...
Historically, the training of deep artificial neural networks has relied on parallel computing to achieve practical effectiveness.
However, with the increas...
Come support two GERAD students participating in the Three-Minute Thesis (3MT) competition. The Polytechnique community is invited to vote for their favourite presentation until April 23, 2021!
Solène Kojtych, Optimisation de boîtes noires discontinues : application à la conception d'aubes de turbomachines robustes aux interactions de contact
Ludovic Salomon, Optimisation multiobjectifs de boîtes noires sous contraintes générales