Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Dehaene, Guillaume"'
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 approximation family or of the target can improve the convergence speed s
Externí odkaz:
http://arxiv.org/abs/1906.06914
Autor:
Dehaene, Guillaume P.
Bernstein-von Mises results (BvM) establish that the Laplace approximation is asymptotically correct in the large-data limit. However, these results are inappropriate for computational purposes since they only hold over most, and not all, datasets an
Externí odkaz:
http://arxiv.org/abs/1904.02505
Autor:
Dehaene, Guillaume
L'inférence bayésienne répond aux questions clés de la perception, comme par exemple : "Que faut-il que je crois étant donné ce que j'ai perçu ?". Elle est donc par conséquent une riche source de modèles pour les sciences cognitives et les n
Externí odkaz:
http://www.theses.fr/2016USPCB189
Autor:
Dehaene, Guillaume P.
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 this work, we present a theorem upper-bounding the KL divergence betwee
Externí odkaz:
http://arxiv.org/abs/1711.08911
Autor:
Dehaene, Guillaume P.
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 uncomputable. Expectation Propagation (EP) (Minka (2001)) is a popular algorithm
Externí odkaz:
http://arxiv.org/abs/1612.05053
Autor:
Dehaene, Guillaume P, Barthelmé, Simon
Publikováno v:
Advances in Neural Information Processing Systems 28, 244--252, 2015
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 made by EP can be bounded. Our bounds have an asymptotic interpretation
Externí odkaz:
http://arxiv.org/abs/1601.02387
Autor:
Dehaene, Guillaume, Barthelmé, Simon
Expectation Propagation (Minka, 2001) is a widely successful algorithm for variational inference. EP is an iterative algorithm used to approximate complicated distributions, typically to find a Gaussian approximation of posterior distributions. In ma
Externí odkaz:
http://arxiv.org/abs/1503.08060
Autor:
Dehaene, Guillaume, Barthelmé, Simon
Publikováno v:
Journal of the Royal Statistical Society. Series B (Statistical Methodology), 2018 Jan 01. 80(1), 199-217.
Externí odkaz:
https://www.jstor.org/stable/44681800
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Dehaene, Guillaume P.1 (AUTHOR) guillaume.dehaene@gmail.com, Coen-Cagli, Ruben1,2 (AUTHOR), Pouget, Alexandre1,3 (AUTHOR)
Publikováno v:
PLoS Computational Biology. 2/12/2021, Vol. 17 Issue 2, p1-30. 30p. 1 Diagram, 5 Graphs.