Poster
Joint control variate for faster black-box variational inference
Xi Wang · · Justin Domke
Multipurpose Room 2 - Number 161
[
Abstract
]
Abstract:
Black-box variational inference performance is sometimes hindered by the use of gradient estimators with high variance. This variance comes from two sources of randomness: Data subsampling and Monte Carlo sampling. While existing control variates only address Monte Carlo noise, and incremental gradient methods typically only address data subsampling, we propose a new "joint" control variate that jointly reduces variance from both sources of noise. This significantly reduces gradient variance, leading to faster optimization in several applications.
Live content is unavailable. Log in and register to view live content