机制独立性：可识别解耦表示的一个原则
Mechanistic Independence: A Principle for Identifiable Disentangled Representations
AI总结：
本文提出机制独立性原则，通过解耦表示中的机制作用来识别潜在子空间，建立独立性准则层级并提供图论特征描述，无需依赖统计假设。
摘要：
本文提出机制独立性原则，通过解耦表示中的机制作用来识别潜在子空间，建立独立性准则层级并提供图论特征描述，无需依赖统计假设。
英文摘要：
Disentangled representations seek to recover latent factors of variation underlying observed data, yet their identifiability is still not fully understood. We introduce a unified framework in which disentanglement is achieved through mechanistic independence, which characterizes latent factors by how they act on observed variables rather than by their latent distribution. This perspective is invariant to changes of the latent density, even when such changes induce statistical dependencies among factors. Within this framework, we propose several related independence criteria -- ranging from support-based and sparsity-based to higher-order conditions -- and show that each yields identifiability of latent subspaces, even under nonlinear, non-invertible mixing. We further establish a hierarchy among these criteria and provide a graph-theoretic characterization of latent subspaces as connected components. Together, these results clarify the conditions under which disentangled representations can be identified without relying on statistical assumptions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
