TY - GEN
T1 - Hierarchical variational models
AU - Ranganath, Rajesh
AU - Tran, Dustin
AU - Blei, David M.
N1 - Funding Information:
This work is supported by NSF IIS-0745520, IIS-1247664, IIS-1009542, ONR N00014-11-1-0651, DARPA FA8750-14-2-0009, N66001-15-C-4032, Facebook, Adobe, Amazon, NVIDIA, the Porter Ogden Jacobus Fellowship, the Seibel Foundation, and John Templeton Foundations.
PY - 2016
Y1 - 2016
N2 - Black box variational inference allows researchers to easily prototype and evaluate an array of models. Recent advances allow such algorithms to scale to high dimensions. However, a central question remains: How to specify an expressive variational distribution that maintains efficient computation? To address this, we develop hierarchical variational models (HVMS). HVMS augment a variational approximation with a prior on its parameters, which allows it to capture complex structure for both discrete and continuous latent variables. The algorithm we develop is black box, can be used for any HVM, and has the same computational efficiency as the original approximation. We study hvms on a variety of deep discrete latent variable models. HVMs generalize other expressive variational distributions and maintains higher fidelity to the posterior.
AB - Black box variational inference allows researchers to easily prototype and evaluate an array of models. Recent advances allow such algorithms to scale to high dimensions. However, a central question remains: How to specify an expressive variational distribution that maintains efficient computation? To address this, we develop hierarchical variational models (HVMS). HVMS augment a variational approximation with a prior on its parameters, which allows it to capture complex structure for both discrete and continuous latent variables. The algorithm we develop is black box, can be used for any HVM, and has the same computational efficiency as the original approximation. We study hvms on a variety of deep discrete latent variable models. HVMs generalize other expressive variational distributions and maintains higher fidelity to the posterior.
UR - http://www.scopus.com/inward/record.url?scp=84997769529&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84997769529&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84997769529
T3 - 33rd International Conference on Machine Learning, ICML 2016
SP - 515
EP - 528
BT - 33rd International Conference on Machine Learning, ICML 2016
A2 - Balcan, Maria Florina
A2 - Weinberger, Kilian Q.
PB - International Machine Learning Society (IMLS)
T2 - 33rd International Conference on Machine Learning, ICML 2016
Y2 - 19 June 2016 through 24 June 2016
ER -