Score Function Gradient Estimation
Score Function Gradient Estimation is a gradient estimation method in variational inference that leverages the score function—the gradient of the log-density of the variational distribution—to compute unbiased but high-variance gradients of the evidence lower bound with respect to distributional parameters by differentiating through the sampling process via the likelihood ratio method.
31
Publications
2K
Citations
89
Authors
37
Institutions
Publications per year
2017–2026
19
Variants
Likelihood Ratio Gradient Estimation
Parents
31
SmoothGrad: removing noise by adding noise
Daniel Smilkov, Nikhil Thorat, Been Kim et al. · arXiv (Cornell University) · 2017 · 755 citations · Full text
Monte Carlo Gradient Estimation in Machine Learning
Shakir Mohamed, Mihaela Rosca, Michael Figurnov et al. · arXiv (Cornell University) · 2019 · 85 citations · Full text
1–5 of 31
89
2
h-index
2
h-index
2
h-index
2
h-index
2
h-index
1–5 of 89
37
Technion – Israel Institute of Technology
Haifa, Israel
3 h-index
3 publications
140 citations
Princeton University
Princeton, United States
2 h-index
4 publications
184 citations
University of Cambridge
Cambridge, United Kingdom
2 h-index
3 publications
69 citations
University of Maryland, Baltimore County
Baltimore, United States
2 h-index
2 publications
65 citations

Athens University of Economics and Business
Athens, Greece
1 h-index
1 publications
27 citations
University of California, Davis
Davis, United States
1 h-index
3 publications
63 citations

Shanghai Jiao Tong University
Shanghai, China
1 h-index
1 publications
24 citations
Columbia University
New York, United States
1 h-index
2 publications
54 citations
1–8 of 37
Repository · 11 publications · 1.1K citations
10
h-index
1 publications · 24 citations
1
h-index
1 publications · 88 citations
1
h-index
1 publications · 13 citations
1
h-index
Conference · 1 publications · 21 citations
1
h-index
1–5