# Probabilistic Meta-Representations Of Neural Networks

arXiv: https://arxiv.org/abs/1810.00555 · HTML: https://mlsanity.com/paper/1810.00555/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2018.

## Built on by (most cited first, 7 of 7)

- [Priors in Bayesian Deep Learning: A Review](https://mlsanity.com/paper/2105.06868/) (2021)
- [Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI](https://mlsanity.com/paper/2402.00809/) (2024)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [Tackling covariate shift with node-based Bayesian neural networks](https://mlsanity.com/paper/2206.02435/) (2022)
- [TyXe: Pyro-based Bayesian neural nets for Pytorch](https://mlsanity.com/paper/2110.00276/) (2021)
- [Compact and Optimal Deep Learning with Recurrent Parameter Generators](https://mlsanity.com/paper/2107.07110/) (2021)
- [Implicit Variational Inference for High-Dimensional Posteriors](https://mlsanity.com/paper/2310.06643/) (2023)

## Abstract (arXiv)

Existing Bayesian treatments of neural networks are typically characterized by weak prior and approximate posterior distributions according to which all the weights are drawn independently. Here, we consider a richer prior distribution in which units in the network are represented by latent variables, and the weights between units are drawn conditionally on the values of the collection of those variables. This allows rich correlations between related weights, and can be seen as realizing a function prior with a Bayesian complexity regularizer ensuring simple solutions. We illustrate the resulting meta-representations and representations, elucidating the power of this prior.