Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Models

Understand

Amortised inference enables scalable learning of sequential latent-variable models (LVMs) with the evidence lower bound (ELBO).

• In this setting, variational posteriors are often only partially conditioned.
• While the true posteriors depend, e.g., on the entire sequence of observations, approximate posteriors are only informed by past observations.
• This mimics the Bayesian filter -- a mixture of smoothing posteriors.