RAMP: Recognition parametrisation by Amortised Message Passing

Lior Fox, Kai Biegun, James Heald, Samo Hromadka, Arielle Rosinski, Maneesh Sahani
Proceedings of The 1st Symposium on Probabilistic Machine Learning, PMLR 327:367-397, 2026.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v327-fox26a, title = {{RAMP}: Recognition parametrisation by Amortised Message Passing}, author = {Fox, Lior and Biegun, Kai and Heald, James and Hromadka, Samo and Rosinski, Arielle and Sahani, Maneesh}, booktitle = {Proceedings of The 1st Symposium on Probabilistic Machine Learning}, pages = {367--397}, year = {2026}, editor = {Swaroop, Siddharth and Rügamer, David and Kristiadi, Agustinus}, volume = {327}, series = {Proceedings of Machine Learning Research}, month = {05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v327/main/assets/fox26a/fox26a.pdf}, url = {https://proceedings.mlr.press/v327/fox26a.html}, abstract = { 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. } }
Endnote
%0 Conference Paper %T RAMP: Recognition parametrisation by Amortised Message Passing %A Lior Fox %A Kai Biegun %A James Heald %A Samo Hromadka %A Arielle Rosinski %A Maneesh Sahani %B Proceedings of The 1st Symposium on Probabilistic Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Siddharth Swaroop %E David Rügamer %E Agustinus Kristiadi %F pmlr-v327-fox26a %I PMLR %P 367--397 %U https://proceedings.mlr.press/v327/fox26a.html %V 327 %X 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.
APA
Fox, L., Biegun, K., Heald, J., Hromadka, S., Rosinski, A. & Sahani, M.. (2026). RAMP: Recognition parametrisation by Amortised Message Passing. Proceedings of The 1st Symposium on Probabilistic Machine Learning, in Proceedings of Machine Learning Research 327:367-397 Available from https://proceedings.mlr.press/v327/fox26a.html.

Related Material