Search Results for author:
Found 4 papers, 1 papers with code
Robust, Automated, and Accurate Black-box Variational Inference
RAABBVI adaptively decreases the learning rate by detecting convergence of the fixed--learning-rate iterates, then estimates the symmetrized Kullback--Leiber (KL) divergence between the current variational approximation and the optimal one.
Challenges for BBVI with Normalizing Flows
Current black-box variational inference (BBVI) methods require the user to make numerous design choices---such as the selection of variational objective and approximating family---yet there is little principled guidance on how to do so.
Challenges and Opportunities in High Dimensional Variational Inference
Our framework and supporting experiments help to distinguish between the behavior of BBVI methods for approximating low-dimensional versus moderate-to-high-dimensional posteriors.
Challenges and Opportunities in High-dimensional Variational Inference
Our framework and supporting experiments help to distinguish between the behavior of BBVI methods for approximating low-dimensional versus moderate-to-high-dimensional posteriors.
