Hierarchical Variational Models is a variational inference framework that introduces a structured prior over latent variables by employing a hierarchy of latent representations, thereby enabling more flexible and expressive posterior approximations compared to mean-field approximations.
79
Publications
5.1K
Citations
258
Authors
109
Institutions
Publications per year
2017–2026
60
Parents
Publications
79
1–5 of 79
Authors
258
- KR
4
h-index
- AH
4
h-index
- EH
4
h-index
- ND
4
h-index
- MZ
4
h-index
1–5 of 258
Institutions
109
Columbia University
New York, United States
4 h-index
8 publications
474 citations
Princeton University
Princeton, United States
4 h-index
5 publications
381 citations
Massachusetts Institute of Technology
Cambridge, United States
4 h-index
10 publications
765 citations
University of Edinburgh
Edinburgh, United Kingdom
3 h-index
8 publications
191 citations
University of California, Berkeley
Berkeley, United States
2 h-index
2 publications
52 citations
National University of Singapore
Singapore, Singapore
2 h-index
4 publications
134 citations
Duke University
Durham, United States
2 h-index
4 publications
151 citations
East China Normal University
Shanghai, China
2 h-index
6 publications
174 citations
1–8 of 109
Venues
- arXiv (Cornell University)
Repository · 25 publications · 1.2K citations
20
h-index
- IEEE Transactions on Pattern Analysis and Machine Intelligence
TPAMI · 3 publications · 86 citations
3
h-index
- Neural Information Processing Systems
Conference · 2 publications · 210 citations
2
h-index
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Conference · 2 publications · 49 citations
2
h-index
- IEEE Transactions on Neural Networks and Learning Systems
2 publications · 147 citations
2
h-index
1–5