Poster
The Variational Predictive Natural Gradient
Da Tang · Rajesh Ranganath

Wed Jun 12th 06:30 -- 09:00 PM @ Pacific Ballroom #234

Variational inference transforms posterior inference into parametric optimization thereby enabling the use of latent variable models where otherwise impractical. However, variational inference can be finicky when different variational parameters control variables that are strongly correlated under the model. Traditional natural gradients based on the variational approximation fail to correct for correlations when the approximation is not the true posterior. To address this, we construct a new natural gradient called the Variational Predictive Natural Gradient (VPNG). Unlike traditional natural gradients for variational inference, this natural gradient accounts for the relationship between model parameters and variational parameters. We demonstrate the insight with a simple example as well as the empirical value on a classification task, a deep generative model of images, and probabilistic matrix factorization for recommendation.

Author Information

Da Tang (Columbia University)
Rajesh Ranganath (New York University)

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

More from the Same Authors