analiza aiqbench
RAMP introduces a novel amortised message-passing framework for unsupervised learning that efficiently recovers latent structures in complex high-dimensional datasets without relying on tractable belief propagation or poor approximations. This method advances the recognition-parametrised modelling paradigm by enabling scalable inference within expressive nonlinear probabilistic models, addressing key bottlenecks in current distributional choices.
RAMP: Recognition parametrisation by Amortised Message Passing
arXiv:2607.18883v1 Announce Type: cross 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.
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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2607.18883 [cs.LG]
(or arXiv:2607.18883v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.18883 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 211 cuvinte
Subiecte conexe
This Teen Helped Native American Students Earn Ham Radio Licenses
IEEE Spectrum · 31 aug. 2026
This Teen Helped Native American Students Earn Ham Radio Licenses
IEEE Spectrum · 31 aug. 2026
From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning
arXiv · 11 iun. 2026
When your brain works differently, AI isn’t a luxury—it’s accessibility
AWS · 13 iul. 2026