Saved in:
Bibliographic Details
Main Authors: Wang, Xi, Geffner, Tomas, Domke, Justin
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2210.07290
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.