Search Results for author:
Found 4 papers, 0 papers with code
Scaling up Stochastic Gradient Descent for Non-convex Optimisation
We propose a unified distributed and parallel implementation of SGD (named DPSGD) that relies on both asynchronous distribution and lock-free parallelism.
Adaptive Experience Selection for Policy Gradient
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.
Online Gaussian LDA for Unsupervised Pattern Mining from Utility Usage Data
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.
Asynchronous Stochastic Variational Inference
Stochastic variational inference (SVI) employs stochastic optimization to scale up Bayesian computation to massive data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
