An Inertial Newton Algorithm for Deep Learning
Résumé
We introduce an inertial second-order method for machine learning, exploiting the geometry of the loss function while requiring only stochastic approximations function values and generalized gradients. The method features a simple mechanical interpretation and we describe promising numerical results on deep learning benchmarks. We give convergence guarantees in a theoretical framework encompassing most deep learning losses under very mild assumptions.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|