Loading...
Thumbnail Image
Publication

Towards Automatic and Robust Variational Inference

Abstract
Variational Inference performance strongly depends on many algorithmic choices, such as the optimization algorithm used, the objective, and the variational family. While the right combination for these components is highly problem dependent, there is currently little guidance on how to find it. This limits the use of these methods by non-expert users. This thesis advances Variational Inference towards an automatic and robust technology. We provide theoretically justified guiding principles for these decisions, and algorithms able to make optimal choices adaptively, creating Variational Inference based tools that are robust, flexible, and widely accessible.
Type
openaccess
article
dissertation
Date
Publisher
Rights
License
http://creativecommons.org/licenses/by-nc/4.0/
Research Projects
Organizational Units
Journal Issue
Embargo
2024-08-01T00:00:00-07:00
Publisher Version
Embedded videos
Collections