1W Minds Feb 6, 2025: Yingzhen Li (Imperial College London), On the Identifiability of Switching...

One of my research dreams is to build a high-resolution video generation model that enables granularity controls in e.g., the scene appearance and the interactions between objects. I tried, and then realised the need of me inventing deep learning tricks for this goal is due to the issue of non-identifiability in my sequential deep generative models. In this talk I will discuss our research towards developing identifiable deep generative models in sequence modelling, and share some recent and on-going works regarding switching dynamic models. In particular, we first show conditions of identifiability for Markov Switching Models (or auto-regressive HMMs) with non-linear transitions, with a new proof technique different from the algebraic approach of the seminal HMM identifiability work by Allman et al. 2009. Then we lift the Markov Switching Model to latent space and leverage existing results to show identifiability. If time permits, I will also show recent developments that build in more flexible structures in the latent switching dynamical prior.
More information about the 1W minds seminar on our homepage: sites.google.c...