发表机构
Gatsby Computational Neuroscience Unit; Centre for Artificial Intelligence（盖茨比计算神经科学单元; 人工智能中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
无监督学习旨在揭示潜在因素，概率模型有局限。本文基于新范式提出RAMP方法，通过学习摊销消息传递框架隐式定义潜在结构，能在复杂高维数据的非线性模型中有效基于似然恢复潜在变量分布。
AI 中文摘要
无监督学习的核心目标是揭示解释观测值之间依赖性的潜在因素。概率模型通常通过引入通过条件关系图链接的多个潜在变量来实现这一点，分布参数及其依赖性从数据中学习。学习依赖于允许易于处理的信念传播的分布选择，或依赖于与模型大小和复杂性缩放不佳的近似。我们基于最近开发的识别参数化建模范式提出了一种替代方法：RAMP，一种通过学习灵活、非线性、摊销消息传递框架来隐式定义潜在结构的方法。我们表明，RAMP能够在作用于复杂高维数据的表达性非线性模型中有效地基于似然恢复潜在变量分布。
英文摘要
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.
CommentsIn the proceedings of the Symposium on Probabilistic Machine Learning 2026 (ProbML 2026)
