# Amortised Inference in Neural Networks for Small-Scale Probabilistic Meta-Learning

arXiv: https://arxiv.org/abs/2310.15786 · HTML: https://mlsanity.com/paper/2310.15786/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 12 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 10 of 10)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Conditional Neural Processes](https://mlsanity.com/paper/1807.01613/) (2018)
- [Neural Processes](https://mlsanity.com/paper/1807.01622/) (2018)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [Bayesian Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1806.03836/) (2018)
- [Convolutional Conditional Neural Processes](https://mlsanity.com/paper/1910.13556/) (2019)
- [Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes](https://mlsanity.com/paper/1906.07697/) (2019)
- [Meta-Learning Probabilistic Inference For Prediction](https://mlsanity.com/paper/1805.09921/) (2018)
- [Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes](https://mlsanity.com/paper/2007.01332/) (2020)
- [Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes](https://mlsanity.com/paper/2005.08140/) (2020)

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

- [Weight-Space Linear Recurrent Neural Networks](https://mlsanity.com/paper/2506.01153/) (2025)
- [Sparse Gaussian Neural Processes](https://mlsanity.com/paper/2504.01650/) (2025)
- [Amortising Inference and Meta-Learning Priors in Neural Networks](https://mlsanity.com/paper/2602.08782/) (2026)

## Abstract (arXiv)

The global inducing point variational approximation for BNNs is based on using a set of inducing inputs to construct a series of conditional distributions that accurately approximate the conditionals of the true posterior distribution. Our key insight is that these inducing inputs can be replaced by the actual data, such that the variational distribution consists of a set of approximate likelihoods for each datapoint. This structure lends itself to amortised inference, in which the parameters of each approximate likelihood are obtained by passing each datapoint through a meta-model known as the inference network. By training this inference network across related datasets, we can meta-learn Bayesian inference over task-specific BNNs.