DeepAI AI Chat
Log In Sign Up

Practical Posterior Error Bounds from Variational Objectives

by   Jonathan H. Huggins, et al.

Variational inference has become an increasingly attractive, computationally efficient 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 accuracy measures for variational approximations 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 computationally efficient for variational inference in that 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 variational inference. Finally, we demonstrate the utility of our proposed workflow and error bounds on a real-data example with a widely used multilevel hierarchical model.


page 1

page 2

page 3

page 4


Practical bounds on the error of Bayesian posterior approximations: A nonasymptotic approach

Bayesian inference typically requires the computation of an approximatio...

Fixing Variational Bayes: Deterministic Variational Inference for Bayesian Neural Networks

Bayesian neural networks (BNNs) hold great promise as a flexible and pri...

Inference for determinantal point processes without spectral knowledge

Determinantal point processes (DPPs) are point process models that natur...

Variational Inference via χ-Upper Bound Minimization

Variational inference (VI) is widely used as an efficient alternative to...

A Targeted Accuracy Diagnostic for Variational Approximations

Variational Inference (VI) is an attractive alternative to Markov Chain ...

Variational Inference with Locally Enhanced Bounds for Hierarchical Models

Hierarchical models represent a challenging setting for inference algori...

Rate Optimal Variational Bayesian Inference for Sparse DNN

Sparse deep neural network (DNN) has drawn much attention in recent stud...

Code Repositories


Efficient, lightweight variational inference and approximation bounds

view repo