# Meta-Amortized Variational Inference and Learning

arXiv: https://arxiv.org/abs/1902.01950 · HTML: https://mlsanity.com/paper/1902.01950/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2019.

## Built on by (most cited first, 22 of 22)

- [ATT3D: Amortized Text-to-3D Object Synthesis](https://mlsanity.com/paper/2306.07349/) (2023)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis](https://mlsanity.com/paper/2403.15385/) (2024)
- [Few-Shot Diffusion Models](https://mlsanity.com/paper/2205.15463/) (2022)
- [Sensitivity-Aware Amortized Bayesian Inference](https://mlsanity.com/paper/2310.11122/) (2023)
- [Learning Prototype-oriented Set Representations for Meta-Learning](https://mlsanity.com/paper/2110.09140/) (2021)
- [Top-Down Visual Attention from Analysis by Synthesis](https://mlsanity.com/paper/2303.13043/) (2023)
- [Amortized Projection Optimization for Sliced Wasserstein Generative Models](https://mlsanity.com/paper/2203.13417/) (2022)
- [Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation](https://mlsanity.com/paper/2502.02463/) (2025)
- [Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models](https://mlsanity.com/paper/2504.17660/) (2025)
- [Compositional simulation-based inference for time series](https://mlsanity.com/paper/2411.02728/) (2024)
- [Partition Function Estimation: A Quantitative Study](https://mlsanity.com/paper/2105.11132/) (2021)
- [SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation](https://mlsanity.com/paper/2110.12279/) (2021)
- [Foundation Posteriors for Approximate Probabilistic Inference](https://mlsanity.com/paper/2205.09735/) (2022)
- [Learning to solve Bayesian inverse problems: An amortized variational inference approach using Gaussian and Flow guides](https://mlsanity.com/paper/2305.20004/) (2023)
- [ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models](https://mlsanity.com/paper/2106.12248/) (2021)
- [Meta-Statistical Learning: Supervised Learning of Statistical Estimators](https://mlsanity.com/paper/2502.12088/) (2025)
- [Meta-Learning an Inference Algorithm for Probabilistic Programs](https://mlsanity.com/paper/2103.00737/) (2021)
- [Tensorizing flows: a tool for variational inference](https://mlsanity.com/paper/2305.02460/) (2023)
- [Bayesian Meta-Reinforcement Learning with Laplace Variational Recurrent Networks](https://mlsanity.com/paper/2505.18591/) (2025)
- [Amortized Factor Inference Networks for Posterior Inference](https://mlsanity.com/paper/2605.26419/) (2026)
- [Amortized Variational Inference of Latent Intensities from Replicated Point Patterns](https://mlsanity.com/paper/2610.16669/) (2026)

## Abstract (arXiv)

Despite the recent success in probabilistic modeling and their applications, generative models trained using traditional inference techniques struggle to adapt to new distributions, even when the target distribution may be closely related to the ones seen during training. In this work, we present a doubly-amortized variational inference procedure as a way to address this challenge. By sharing computation across not only a set of query inputs, but also a set of different, related probabilistic models, we learn transferable latent representations that generalize across several related distributions. In particular, given a set of distributions over images, we find the learned representations to transfer to different data transformations. We empirically demonstrate the effectiveness of our method by introducing the MetaVAE, and show that it significantly outperforms baselines on downstream image classification tasks on MNIST (10-50%) and NORB (10-35%).