AI RESEARCH
End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems
arXiv CS.LG
•
ArXi:2605.06315v1 Announce Type: cross 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