Validated Variational Inference via Practical Posterior Error Bounds
This addresses the problem of validating variational inference accuracy for practitioners, though it is incremental as it builds on existing variational methods.
The paper tackles the lack of post-hoc accuracy measures in variational inference by providing rigorous and computationally efficient error bounds for posterior mean and uncertainty estimates, demonstrating utility on a robust regression problem and a real-data hierarchical model.
Variational inference has become an increasingly attractive fast alternative to Markov chain Monte Carlo methods for approximate Bayesian inference. However, a major obstacle to the widespread use of variational methods is the lack of post-hoc accuracy measures that are both theoretically justified and computationally efficient. In this paper, we provide rigorous bounds on the error of posterior mean and uncertainty estimates that arise from full-distribution approximations, as in variational inference. Our bounds are widely applicable, as they require only that the approximating and exact posteriors have polynomial moments. Our bounds are also computationally efficient for variational inference because they require only standard values from variational objectives, straightforward analytic calculations, and simple Monte Carlo estimates. We show that our analysis naturally leads to a new and improved workflow for validated variational inference. Finally, we demonstrate the utility of our proposed workflow and error bounds on a robust regression problem and on a real-data example with a widely used multilevel hierarchical model.