Yes, but Did It Work?: Evaluating Variational Inference


Yuling Yao, Aki Vehtari, Daniel Simpson, Andrew Gelman ;
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5581-5590, 2018.


While it’s always possible to compute a variational approximation to a posterior distribution, it can be difficult to discover problems with this approximation. We propose two diagnostic algorithms to alleviate this problem. The Pareto-smoothed importance sampling (PSIS) diagnostic gives a goodness of fit measurement for joint distributions, while simultaneously improving the error in the estimate. The variational simulation-based calibration (VSBC) assesses the average performance of point estimates.

Related Material