The reparameterization gradient has become a widely used method to obtain Monte Carlo gradients to optimize the variational objective. However, this technique does not easily apply to commonly used distributions such as beta or gamma without further approximations, and most practical applications of the reparameterization gradient fit Gaussian distributions. In this paper, we introduce the generalized repa-rameterization gradient, a method that extends the reparameterization gradient to a wider class of variational distributions. Generalized reparameterizations use invert-ible transformations of the latent variables which lead to transformed distributions that weakly depend on the variational parameters. This results in new Monte Carlo grad...
International audienceMotivated by penalized likelihood maximization in complex models, we study opt...
A case is made for the use of hierarchical models in the analysis of generalization gradients. Hiera...
A case is made for the use of hierarchical models in the analysis of generalization gradients. Hiera...
Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparame...
We investigate a local reparameterizaton technique for greatly reducing the variance of stochastic g...
In this paper we consider efficient message passing based inference in a factor graph representation...
Discrete expectations arise in various machine learning tasks, and we often need to backpropagate th...
Variational inference approximates the posterior distribution of a probabilistic model with a parame...
International audienceThe generalized likelihood ratio (GLR) method is a recently introduced gradien...
This paper introduces the $\textit{variational Rényi bound}$ (VR) that extends traditional variation...
Variational Gaussian (VG) inference methods that optimize a lower bound to the marginal likelihood a...
The field of statistical machine learning has seen a rapid progress in complex hierarchical Bayesian...
Gradient estimation is often necessary for fitting generative models with discrete latent variables,...
Policy gradient methods are reinforcement learning algorithms that adapt a pa-rameterized policy by ...
The Gumbel-Softmax is a continuous distribution over the simplex that is often used as a relaxation ...
International audienceMotivated by penalized likelihood maximization in complex models, we study opt...
A case is made for the use of hierarchical models in the analysis of generalization gradients. Hiera...
A case is made for the use of hierarchical models in the analysis of generalization gradients. Hiera...
Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparame...
We investigate a local reparameterizaton technique for greatly reducing the variance of stochastic g...
In this paper we consider efficient message passing based inference in a factor graph representation...
Discrete expectations arise in various machine learning tasks, and we often need to backpropagate th...
Variational inference approximates the posterior distribution of a probabilistic model with a parame...
International audienceThe generalized likelihood ratio (GLR) method is a recently introduced gradien...
This paper introduces the $\textit{variational Rényi bound}$ (VR) that extends traditional variation...
Variational Gaussian (VG) inference methods that optimize a lower bound to the marginal likelihood a...
The field of statistical machine learning has seen a rapid progress in complex hierarchical Bayesian...
Gradient estimation is often necessary for fitting generative models with discrete latent variables,...
Policy gradient methods are reinforcement learning algorithms that adapt a pa-rameterized policy by ...
The Gumbel-Softmax is a continuous distribution over the simplex that is often used as a relaxation ...
International audienceMotivated by penalized likelihood maximization in complex models, we study opt...
A case is made for the use of hierarchical models in the analysis of generalization gradients. Hiera...
A case is made for the use of hierarchical models in the analysis of generalization gradients. Hiera...