# RAMP: Recognition parametrisation by Amortised Message Passing

arXiv: https://arxiv.org/abs/2607.18883 · HTML: https://mlsanity.com/paper/2607.18883/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 38 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 17 of 17)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Deep learning for universal linear embeddings of nonlinear dynamics](https://mlsanity.com/paper/1712.09707/) (2017)
- [Black Box Variational Inference](https://mlsanity.com/paper/1401.0118/) (2013)
- [Modern Koopman Theory for Dynamical Systems](https://mlsanity.com/paper/2102.12086/) (2021)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [Expectation Propagation for approximate Bayesian inference](https://mlsanity.com/paper/1301.2294/) (2013)
- [Composing graphical models with neural networks for structured representations and fast inference](https://mlsanity.com/paper/1603.06277/) (2016)
- [Loopy Belief Propagation for Approximate Inference: An Empirical Study](https://mlsanity.com/paper/1301.6725/) (2013)
- [3D Human Pose Estimation from a Single Image via Distance Matrix Regression](https://mlsanity.com/paper/1611.09010/) (2016)
- [Robust Estimation of 3D Human Poses from a Single Image](https://mlsanity.com/paper/1406.2282/) (2014)
- [Temporally Consistent Koopman Autoencoders for Forecasting Dynamical Systems](https://mlsanity.com/paper/2403.12335/) (2024)
- [Revisiting Structured Variational Autoencoders](https://mlsanity.com/paper/2305.16543/) (2023)
- [Unsupervised representation learning with recognition-parametrised probabilistic models](https://mlsanity.com/paper/2209.05661/) (2022)
- [Maximum Likelihood Learning of Latent Dynamics Without Reconstruction](https://mlsanity.com/paper/2505.23569/) (2025)
- [Expectation Particle Belief Propagation](https://mlsanity.com/paper/1506.05934/) (2015)
- [Graph Neural Networks Gone Hogwild](https://mlsanity.com/paper/2407.00494/) (2024)

## Abstract (arXiv)

A central aim of unsupervised learning is to uncover latent factors that explain dependencies among observations. Probabilistic models typically achieve this by introducing multiple latent variables linked through a graph of conditional relationships, with distributional parameters and their dependence learnt from data. Learning relies either on distributional choices that allow tractable belief propagation, or on approximations that scale poorly with model size and complexity. We build on the recently developed recognition-parametrised modelling paradigm to propose an alternative approach: RAMP, a method that implicitly defines latent structure by learning a flexible, nonlinear, amortised message-passing framework. We show that RAMP enables efficient likelihood-based recovery of latent-variable distributions within expressive nonlinear models acting on complex high-dimensional data.