Timezone: »

 
Poster
Divide and Couple: Using Monte Carlo Variational Objectives for Posterior Approximation
Justin Domke · Daniel Sheldon

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #166
in Probabilistic Methods -- Variational Inference »

Recent work in variational inference (VI) has used ideas from Monte Carlo estimation to obtain tighter lower bounds on the log-likelihood to be used as objectives for VI. However, there is not a systematic understanding of how optimizing different objectives relates to approximating the posterior distribution. Developing such a connection is important if the ideas are to be applied to inference—i.e., applications that require an approximate posterior and not just an approximation of the log-likelihood. Given a VI objective defined by a Monte Carlo estimator of the likelihood, we use a "divide and couple" procedure to identify augmented proposal and target distributions so that the gap between the VI objective and the log-likelihood is equal to the divergence between these distributions. Thus, after maximizing the VI objective, the augmented variational distribution may be used to approximate the posterior distribution.

Keywords: Variational Inference · Probabilistic Methods
[ Paper]  [ Poster] 

Author Information

Justin Domke (University of Massachusetts, Amherst)
Daniel Sheldon (University of Massachusetts Amherst)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors