ICML 2020poster44 citations

Provable Smoothness Guarantees for Black-Box Variational Inference

Justin Domke

Abstract

Black-box variational inference tries to approximate a complex target distribution through a gradient-based optimization of the parameters of a simpler distribution. Provable convergence guarantees require structural properties of the objective. This paper shows that for location-scale family approximations, if the target is M-Lipschitz smooth, then so is the “energy” part of the variational objective. The key proof idea is to describe gradients in a certain inner-product space, thus permitting the use of Bessel’s inequality. This result gives bounds on the location of the optimal parameters, and is a key ingredient for convergence guarantees.

BibTeX
@InProceedings{pmlr-v119-domke20a,
  title = 	 {Provable Smoothness Guarantees for Black-Box Variational Inference},
  author =       {Domke, Justin},
  booktitle = 	 {Proceedings of the 37th International Conference on Machine Learning},
  pages = 	 {2587--2596},
  year = 	 {2020},
  editor = 	 {III, Hal Daumé and Singh, Aarti},
  volume = 	 {119},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {13--18 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v119/domke20a/domke20a.pdf},
  url = 	 {https://proceedings.mlr.press/v119/domke20a.html},
  abstract = 	 {Black-box variational inference tries to approximate a complex target distribution through a gradient-based optimization of the parameters of a simpler distribution. Provable convergence guarantees require structural properties of the objective. This paper shows that for location-scale family approximations, if the target is M-Lipschitz smooth, then so is the “energy” part of the variational objective. The key proof idea is to describe gradients in a certain inner-product space, thus permitting the use of Bessel’s inequality. This result gives bounds on the location of the optimal parameters, and is a key ingredient for convergence guarantees.}
}
Provable Smoothness Guarantees for Black-Box Variational Inference · ICML 2020