HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals

Chao Ma, Sebastian Tschiatschek, Yingzhen Li, Richard Turner, Jose Miguel Hernandez-Lobato, Cheng Zhang
Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, PMLR 118:1-8, 2020.

Abstract

In this paper, we propose a very simple but e ective 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 the vanilla VAEs fails.

Cite this Paper

BibTeX
@InProceedings{pmlr-v118-ma20a, title = { HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals}, author = {Ma, Chao and Tschiatschek, Sebastian and Li, Yingzhen and Turner, Richard and Hernandez-Lobato, Jose Miguel and Zhang, Cheng}, booktitle = {Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference}, pages = {1--8}, year = {2020}, editor = {Zhang, Cheng and Ruiz, Francisco and Bui, Thang and Dieng, Adji Bousso and Liang, Dawen}, volume = {118}, series = {Proceedings of Machine Learning Research}, month = {08 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v118/ma20a/ma20a.pdf}, url = {https://proceedings.mlr.press/v118/ma20a.html}, abstract = {In this paper, we propose a very simple but e ective 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 the vanilla VAEs fails. } }
Endnote
%0 Conference Paper %T HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals %A Chao Ma %A Sebastian Tschiatschek %A Yingzhen Li %A Richard Turner %A Jose Miguel Hernandez-Lobato %A Cheng Zhang %B Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference %C Proceedings of Machine Learning Research %D 2020 %E Cheng Zhang %E Francisco Ruiz %E Thang Bui %E Adji Bousso Dieng %E Dawen Liang %F pmlr-v118-ma20a %I PMLR %P 1--8 %U https://proceedings.mlr.press/v118/ma20a.html %V 118 %X In this paper, we propose a very simple but e ective 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 the vanilla VAEs fails.
APA
Ma, C., Tschiatschek, S., Li, Y., Turner, R., Hernandez-Lobato, J.M. & Zhang, C.. (2020). HM-VAEs: a Deep Generative Model for Real-valued Data with Heterogeneous Marginals. Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, in Proceedings of Machine Learning Research 118:1-8 Available from https://proceedings.mlr.press/v118/ma20a.html.

Related Material