← Search

Akash Kumar Dhaka

2 accepted papers

2021

Challenges and Opportunities in High Dimensional Variational Inference

NeurIPS 2021poster

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. We develop a conceptual framework and set of experimental tools…

Cited by 57SourcePDFScholar
2020

Robust, Accurate Stochastic Optimization for Variational Inference

NeurIPS 2020poster

We examine the accuracy of black box variational posterior approximations for parametric models in a probabilistic programming context. The performance of these approximations depends on (1) how well the variational family approximates the true posterior distribution, (2) the choice of divergence, a…

Cited by 42SourcePDFScholar