# Asymptotic Consistency of Loss-Calibrated Variational Bayes

arXiv: https://arxiv.org/abs/1911.01288 · HTML: https://mlsanity.com/paper/1911.01288/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2019.

## Built on by (most cited first, 3 of 3)

- [Approximation-Aware Bayesian Optimization](https://mlsanity.com/paper/2406.04308/) (2024)
- [Bayesian Joint Chance Constrained Optimization: Approximations and Statistical Consistency](https://mlsanity.com/paper/2106.12199/) (2021)
- [Making Reliable and Flexible Decisions in Long-tailed Classification](https://mlsanity.com/paper/2501.14090/) (2025)

## Abstract (arXiv)

This paper establishes the asymptotic consistency of the it loss-calibrated variational Bayes (LCVB) method. LCVB was proposed in~citeLaSiGh2011 as a method for approximately computing Bayesian posteriors in a `loss aware' manner. This methodology is also highly relevant in general data-driven decision-making contexts. Here, we not only establish the asymptotic consistency of the calibrated approximate posterior, but also the asymptotic consistency of decision rules. We also establish the asymptotic consistency of decision rules obtained from a `naive' variational Bayesian procedure.