Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces RAMP, a novel method that utilizes a flexible, nonlinear, amortised message-passing framework to implicitly define latent structures in unsupervised learning. By leveraging this approach, RAMP achieves efficient likelihood-based recovery of latent-variable distributions, addressing the limitations of traditional probabilistic models that struggle with scalability and complexity. The results demonstrate that RAMP outperforms existing methods in handling complex high-dimensional data while maintaining tractable computations.
RAMP revolutionizes latent variable modeling by enabling efficient recovery of distributions in high-dimensional spaces without the scalability issues of traditional methods.
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.