Poster
Provable Gradient Variance Guarantees for Black-Box Variational Inference
Justin Domke
East Exhibition Hall B, C #189
Keywords: [ Probabilistic Methods ] [ Variational Inference ]
Recent variational inference methods use stochastic gradient estimators whose variance is not well understood. Theoretical guarantees for these estimators are important to understand when these methods will or will not work. This paper gives bounds for the common “reparameterization” estimators when the target is smooth and the variational family is a location-scale distribution. These bounds are unimprovable and thus provide the best possible guarantees under the stated assumptions.
Live content is unavailable. Log in and register to view live content