Timezone: »

 
Poster
Importance Weighted Hierarchical Variational Inference
Artem Sobolev · Dmitry Vetrov

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #167
in Probabilistic Methods -- Variational Inference »

Variational Inference is a powerful tool in the Bayesian modeling toolkit, however, its effectiveness is determined by the expressivity of the utilized variational distributions in terms of their ability to match the true posterior distribution. In turn, the expressivity of the variational family is largely limited by the requirement of having a tractable density function. To overcome this roadblock, we introduce a new family of variational upper bounds on a marginal log-density in the case of hierarchical models (also known as latent variable models). We then derive a family of increasingly tighter variational lower bounds on the otherwise intractable standard evidence lower bound for hierarchical variational distributions, enabling the use of more expressive approximate posteriors. We show that previously known methods, such as Hierarchical Variational Models, Semi-Implicit Variational Inference and Doubly Semi-Implicit Variational Inference can be seen as special cases of the proposed approach, and empirically demonstrate superior performance of the proposed method in a set of experiments.

Keywords: Variational Inference · Latent Variable Models · Probabilistic Methods · Probabilistic Methods -> Hierarchical Models; Probabilistic Methods
[ Paper]  [ Poster]  [ Slides] 

Author Information

Artem Sobolev (Samsung AI Center Moscow)
Dmitry Vetrov (Higher School of Economics, Samsung AI Center, Moscow)

More from the Same Authors