1 citations · 1 across the 3 of their papers we have counts for
3 papers
Analysis and Comparison of Two-Level KFAC Methods for Training Deep Neural Networks
Abdoulaye Koroko, Ani Anciaux-Sedrakian, Ibtihel Ben Gharbia +3
As a second-order method, the Natural Gradient Descent (NGD) has the ability to accelerate training of neural networks. However, due to the prohibitive computational and memory cos…
Computing Surface Reaction Rates by Adaptive Multilevel Splitting Combined with Machine Learning and Ab Initio Molecular Dynamics
Thomas Pigeon, Gabriel Stoltz, Manuel Corral-Valero +4
Computing accurate rate constants for catalytic events occurring at the surface of a given material represents a challenging task with multiple potential applications in chemistry.…
Efficient Approximations of the Fisher Matrix in Neural Networks using Kronecker Product Singular Value Decomposition
Abdoulaye Koroko, Ani Anciaux-Sedrakian, Ibtihel Ben Gharbia +3
Several studies have shown the ability of natural gradient descent to minimize the objective function more efficiently than ordinary gradient descent based methods. However, the bo…