提出新模型实现可识别的动态系统建模，提升时序数据解析精度。
End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
- 基于流模型设计精确似然优化方法，突破传统VAE近似瓶颈
- 在合成与真实数据上实现更优解耦与动态预测性能
- 适合研究时序模式切换、需结构可识别性的场景
深度生成模型中学习可识别表征仍是根本挑战，尤其针对具有状态切换特性的时序数据。现有方法通常依赖严苛假设（如平稳性或有限观测模型），且多采用变分自编码器（VAE）估计器，引入近似误差，限制了潜在结构恢复。本文首次在灵活假设下证明了一类广义递归非线性切换动态系统的可识别性，并提出$Ω$SDS——一种基于流的估计器，支持使用期望最大化实现精确似然优化。在合成与真实数据上的实证验证表明，$Ω$SDS相比基于VAE的估计器具有更优的解耦能力与更精准的动态预测性能。
原文摘要 · Abstract (English)
Learning identifiable representations in deep generative models remains a fundamental challenge, particularly for sequential data with regime-switching dynamics. Existing approaches establish identifiability under restrictive assumptions, such as stationarity or limited emission models, and typically rely on variational autoencoder (VAE) estimators, which introduce approximation gaps that limit the recovery of the latent structure. In this work, we address both the theoretical and practical limitations of this setting. First, we establish identifiability of a broad class of recurrent nonlinear switching dynamical systems under flexible assumptions, significantly extending prior results. Second, we introduce $Ω$SDS, a flow-based estimator that enables exact likelihood optimization using expectation-maximisation. Through empirical validation on both synthetic and real-world data, our results demonstrate that $Ω$SDS achieves improved disentanglement compared to VAE-based estimators and more accurate forecasting of underlying dynamics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。