no code implementations • 6 Oct 2022 • Saad Mohamad, Hamad Alamri, Abdelhamid Bouchachia
We propose a unified distributed and parallel implementation of SGD (named DPSGD) that relies on both asynchronous distribution and lock-free parallelism.
no code implementations • 17 Feb 2020 • Saad Mohamad, Giovanni Montana
Existing sampling strategies for experience replay like uniform sampling or prioritised experience replay do not explicitly try to control the variance of the gradient estimates.
no code implementations • 25 Oct 2019 • Saad Mohamad, Abdelhamid Bouchachia
In particular, we develop a new method based on Gaussian Latent Dirichlet Allocation (GLDA) in order to extract global components that summarise the energy signal.
no code implementations • 12 Jan 2018 • Saad Mohamad, Abdelhamid Bouchachia, Moamar Sayed-Mouchaweh
Stochastic variational inference (SVI) employs stochastic optimization to scale up Bayesian computation to massive data.