Likelihood-based Generative Modeling
Likelihood-Based Generative Modeling is a generative modeling paradigm that belongs to the class of probabilistic models and is distinguished by its formulation of a tractable likelihood function, through which the model explicitly learns the probability distribution of the data by maximizing the likelihood of observed samples.
93
Publications
13.5K
Citations
245
Authors
77
Institutions
Publications per year
2017–2026
63
Parents
93
Deep generative modeling for single-cell transcriptomics
Romain Lopez, Jeffrey Regier, Michael B. Cole et al. · Nature Methods · 2018 · 2.6K citations
A note on the evaluation of generative models
Lucas Theis, Aäron van den Oord, Matthias Bethge · arXiv (Cornell University) · 2015 · 436 citations · Full text
1–5 of 93
245
4
h-index
4
h-index
4
h-index
3
h-index
3
h-index
1–5 of 245
77
Google (United States)
Mountain View, United States
9 h-index
17 publications
760 citations
Aalto University
Espoo, Finland
6 h-index
6 publications
487 citations
Helsinki Institute for Information Technology
Espoo, Finland
5 h-index
10 publications
846 citations
Université de Montréal
Montreal, Canada
5 h-index
8 publications
153 citations

University of Toronto
Toronto, Canada
4 h-index
9 publications
520 citations

University of Helsinki
Helsinki, Finland
4 h-index
6 publications
675 citations

University of Edinburgh
Edinburgh, United Kingdom
3 h-index
3 publications
170 citations
University of Oxford
Oxford, United Kingdom
3 h-index
3 publications
4.6K citations
1–8 of 77
Repository · 54 publications · 4.1K citations
29
h-index
AI · 1 publications · 119 citations
1
h-index
PRD · 1 publications · 22 citations
1
h-index
Repository · 1 publications · 12 citations
1
h-index
1 publications · 76 citations
1
h-index
1–5