Add to ORKGWe develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To make inference tractable, we introduce the variational contrastive divergence (VCD), a new divergence that replaces the standard Kullback-Leibler (KL) divergence used in VI. The VCD captures a notion of discrepancy between the initial variational distribution and its improved version (obtained after running the MCMC steps), and it converges asymptotically to the symmetrized KL divergence between the variational distribution and the posterior of interest. The VCD objective can be optimized efficiently with re...
We introduce Auxiliary Variational MCMC, a novel framework for learning MCMC kernels that combines r...
We propose a new method to approximately integrate a function with respect to a given probability di...
This paper analyses the Contrastive Divergence algorithm for learning statistical parameters. We rel...
Recent advances in stochastic gradient variational inference have made it possible to perform variat...
Recent advances in stochastic gradient varia-tional inference have made it possible to perform varia...
Recent advances in stochastic gradient variational inference have made it possi-ble to perform varia...
Many recent advances in large scale probabilistic inference rely on variational methods. The success...
This paper introduces the $\textit{variational Rényi bound}$ (VR) that extends traditional variation...
Contrastive divergence (CD) is a promising method of inference in high dimen-sional distributions wi...
We propose a new class of learning algorithms that combines variational approximation and Markov cha...
Maximum-likelihood (ML) learning of Markov random fields is challenging because it requires estima...
<p>One of the core problems of modern statistics is to approximate difficult-to-compute probability ...
Variational inference methods, including mean field methods and loopy belief propagation, have been ...
Boosting variational inference (BVI) approximates Bayesian posterior distributions by iteratively bu...
We propose Pathfinder, a variational method for approximately sampling from differentiable probabili...
We introduce Auxiliary Variational MCMC, a novel framework for learning MCMC kernels that combines r...
We propose a new method to approximately integrate a function with respect to a given probability di...
This paper analyses the Contrastive Divergence algorithm for learning statistical parameters. We rel...
Recent advances in stochastic gradient variational inference have made it possible to perform variat...
Recent advances in stochastic gradient varia-tional inference have made it possible to perform varia...
Recent advances in stochastic gradient variational inference have made it possi-ble to perform varia...
Many recent advances in large scale probabilistic inference rely on variational methods. The success...
This paper introduces the $\textit{variational Rényi bound}$ (VR) that extends traditional variation...
Contrastive divergence (CD) is a promising method of inference in high dimen-sional distributions wi...
We propose a new class of learning algorithms that combines variational approximation and Markov cha...
Maximum-likelihood (ML) learning of Markov random fields is challenging because it requires estima...
<p>One of the core problems of modern statistics is to approximate difficult-to-compute probability ...
Variational inference methods, including mean field methods and loopy belief propagation, have been ...
Boosting variational inference (BVI) approximates Bayesian posterior distributions by iteratively bu...
We propose Pathfinder, a variational method for approximately sampling from differentiable probabili...
We introduce Auxiliary Variational MCMC, a novel framework for learning MCMC kernels that combines r...
We propose a new method to approximately integrate a function with respect to a given probability di...
This paper analyses the Contrastive Divergence algorithm for learning statistical parameters. We rel...