13 citations · 24 across the 5 of their papers we have counts for
6 papers
Variational Inference with Numerical Derivatives: variance reduction through coupling
Alexander Immer, Guillaume P. Dehaene
The Black Box Variational Inference (Ranganath et al. (2014)) algorithm provides a universal method for Variational Inference, but taking advantage of special properties of the app…
A deterministic and computable Bernstein-von Mises theorem
Guillaume P. Dehaene
Bernstein-von Mises results (BvM) establish that the Laplace approximation is asymptotically correct in the large-data limit. However, these results are inappropriate for computati…
Computing the quality of the Laplace approximation
Guillaume P. Dehaene
Bayesian inference requires approximation methods to become computable, but for most of them it is impossible to quantify how close the approximation is to the true posterior. In t…
Expectation Propagation performs a smoothed gradient descent
Guillaume P. Dehaene
Bayesian inference is a popular method to build learning algorithms but it is hampered by the fact that its key object, the posterior probability distribution, is often uncomputabl…
Bounding errors of Expectation-Propagation
Guillaume P Dehaene, Simon Barthelmé
Expectation Propagation is a very popular algorithm for variational inference, but comes with few theoretical guarantees. In this article, we prove that the approximation errors ma…
Expectation Propagation in the large-data limit
Guillaume Dehaene, Simon Barthelmé
Expectation Propagation (Minka, 2001) is a widely successful algorithm for variational inference. EP is an iterative algorithm used to approximate complicated distributions, typica…