Reparameterization Gradient Estimation
Reparameterization Gradient Estimation is a gradient estimation technique in variational inference that belongs to the class of stochastic gradient methods and differentiates itself by enabling low-variance gradient computation through the explicit reparameterization of random variables with respect to their distributional parameters.
15
Publications
4.1K
Citations
34
Authors
27
Institutions
Publications per year
2017–2026
9
Parents
15
Categorical Reparameterization with Gumbel-Softmax
Eric Jang, Shixiang Gu, Ben Poole · arXiv (Cornell University) · 2016 · 3.2K citations · Full text
Categorical Reparameterization with Gumbel-Softmax
Eric Jang, Shixiang Gu, Ben Poole · arXiv (Cornell University) · 2016 · 217 citations · Full text
1–5 of 15
34
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 34
27

University of Amsterdam
Amsterdam, The Netherlands
1 h-index
2 publications
22 citations
Shinshu University
Matsumoto, Japan
1 h-index
1 publications
52 citations
Research Institute of Animal Husbandry
Ulaanbaatar, Mongolia
1 h-index
1 publications
59 citations
Humboldt-Universität zu Berlin
Berlin, Germany
1 h-index
1 publications
13 citations

National Research University Higher School of Economics
Moscow, Russia
1 h-index
1 publications
86 citations

University of Bucharest
Bucharest, Romania
1 h-index
1 publications
118 citations

University of Toronto
Toronto, Canada
1 h-index
2 publications
146 citations
Columbia University
New York, United States
1 h-index
2 publications
32 citations
1–8 of 27
Repository · 9 publications · 3.7K citations
9
h-index
GSE · 1 publications · 59 citations
1
h-index
Conference · 1 publications · 40 citations
1
h-index
Repository · 1 publications · 11 citations
1
h-index
Conference · 1 publications · 86 citations
1
h-index
1–5