# Improving Explorability in Variational Inference with Annealed Variational Objectives

arXiv: https://arxiv.org/abs/1809.01818 · HTML: https://mlsanity.com/paper/1809.01818/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2018.

## Built on by (most cited first, 24 of 24)

- [Annealed Flow Transport Monte Carlo](https://mlsanity.com/paper/2102.07501/) (2021)
- [Score-Based Diffusion meets Annealed Importance Sampling](https://mlsanity.com/paper/2208.07698/) (2022)
- [MCMC Variational Inference via Uncorrected Hamiltonian Annealing](https://mlsanity.com/paper/2107.04150/) (2021)
- [Monte Carlo Variational Auto-Encoders](https://mlsanity.com/paper/2106.15921/) (2021)
- [Annealed Stein Variational Gradient Descent](https://mlsanity.com/paper/2101.09815/) (2021)
- [Posterior Collapse of a Linear Latent Variable Model](https://mlsanity.com/paper/2205.04009/) (2022)
- [On the Robustness to Misspecification of α-Posteriors and Their Variational Approximations](https://mlsanity.com/paper/2104.08324/) (2021)
- [Out-of-Distribution Detection for Medical Applications: Guidelines for Practical Evaluation](https://mlsanity.com/paper/2109.14885/) (2021)
- [Nested Variational Inference](https://mlsanity.com/paper/2106.11302/) (2021)
- [Controlling Posterior Collapse by an Inverse Lipschitz Constraint on the Decoder Network](https://mlsanity.com/paper/2304.12770/) (2023)
- [Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders](https://mlsanity.com/paper/2306.05023/) (2023)
- [Learning Proposals for Probabilistic Programs with Inference Combinators](https://mlsanity.com/paper/2103.00668/) (2021)
- [Semiparametric inference using fractional posteriors](https://mlsanity.com/paper/2301.08158/) (2023)
- [Posterior Collapse as a Phase Transition in Variational Autoencoders](https://mlsanity.com/paper/2510.01621/) (2025)
- [Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures](https://mlsanity.com/paper/2602.12923/) (2026)
- [AdaAnn: Adaptive Annealing Scheduler for Probability Density Approximation](https://mlsanity.com/paper/2202.00792/) (2022)
- [Covariate-informed Representation Learning to Prevent Posterior Collapse of iVAE](https://mlsanity.com/paper/2202.04206/) (2022)
- [Variational Meta Reinforcement Learning for Social Robotics](https://mlsanity.com/paper/2206.03211/) (2022)
- [BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptation](https://mlsanity.com/paper/2412.09718/) (2024)
- [Variational Laplace for Bayesian neural networks](https://mlsanity.com/paper/2103.00222/) (2021)
- [Learning Sparse Codes with Entropy-Based ELBOs](https://mlsanity.com/paper/2311.01888/) (2023)
- [Variational Sampling of Temporal Trajectories](https://mlsanity.com/paper/2403.11418/) (2024)
- [Quasi Monte Carlo methods enable extremely low-dimensional deep generative models](https://mlsanity.com/paper/2601.18676/) (2026)
- [Spherical VAE with Cluster-Aware Feasible Regions: Guaranteed Prevention of Posterior Collapse](https://mlsanity.com/paper/2603.10935/) (2026)

## Abstract (arXiv)

Despite the advances in the representational capacity of approximate distributions for variational inference, the optimization process can still limit the density that is ultimately learned. We demonstrate the drawbacks of biasing the true posterior to be unimodal, and introduce Annealed Variational Objectives (AVO) into the training of hierarchical variational methods. Inspired by Annealed Importance Sampling, the proposed method facilitates learning by incorporating energy tempering into the optimization objective. In our experiments, we demonstrate our method's robustness to deterministic warm up, and the benefits of encouraging exploration in the latent space.