Effective training of deep neural networks suffers from two main issues. The first is that the
parameter space of these models exhibit pathological curvature. Recent methods address …

Softwares play an important role in controlling complex systems. Monitoring the proper
functioning of the components of such systems is the principal role of softwares. Often, a …

Abstract Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian
analogs to popular stochastic optimization methods; however, this connection is not well …

Learning the representation of shape cues in 2D & 3D objects for recognition is a
fundamental task in computer vision. Deep neural networks (DNNs) have shown promising …

We propose a unifying view of two different Bayesian inference algorithms, Stochastic
Gradient Markov Chain Monte Carlo (SG-MCMC) and Stein Variational Gradient Descent …

In this paper we develop a Stochastic Gradient Langevin Dynamics (SGLD) algorithm
tailored for solving a certain class of non-convex distributionally robust optimisation …

Recurrent neural networks (RNNs) have shown promising performance for language
modeling. However, traditional training of RNNs using back-propagation through time often …

Test log-likelihood is commonly used to compare different models of the same data or
different approximate inference algorithms for fitting the same probabilistic model. We …

A complete recipe of measure-preserving diffusions in Euclidean space was recently
derived unifying several MCMC algorithms into a single framework. In this paper, we …

We introduce a stochastic version of the non-reversible, rejection-free Bouncy Particle
Sampler (BPS), a Markov process whose sample trajectories are piecewise linear, to …