HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals
Abstract
In this paper, we propose a very simple but effective VAE model (HM-VAE) that can handle real-valued data with heterogeneous marginals, meaning that they have drastically distinct marginal distributions, statistical properties as well as semantics. Preliminary results show that the HM-VAE can learn distributions with heterogeneous marginal distributions, whereas vanilla VAEs fails.
Top
- Ma, Chao
- Tschiatschek, Sebastian
- Li, Yingzhen
- Turner, Richard
- Hernandez-Lobato, Jose Miguel
- Zhang, Cheng
Top
Shortfacts
Category |
Paper in Conference Proceedings or in Workshop Proceedings (Poster) |
Event Title |
2nd Symposium on Advances in Approximate Bayesian Inference (AABI) |
Divisions |
Data Mining and Machine Learning |
Subjects |
Kuenstliche Intelligenz Angewandte Informatik |
Event Location |
Vancouver |
Event Type |
Workshop |
Event Dates |
08.12.2019 |
Series Name |
Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference |
Publisher |
PMLR |
Page Range |
118:1-118:8 |
Date |
2020 |
Official URL |
http://proceedings.mlr.press/v118/ma20a.html |
Export |
Top
