GFlowNet-EM for learning compositional latent variable models

Understand

Latent variable models (LVMs) with discrete compositional latents are an important but challenging setting due to a combinatorially large number of possible configurations of the latents.

• A key tradeoff in modeling the posteriors over latents is between expressivity and tractable optimization.
• For algorithms based on expectation-maximization (EM), the E-step is often intractable without restrictive approximations to the posterior.
• We propose the use of GFlowNets, algorithms for sampling from an unnormalized density by learning a stochastic policy for sequential construction of samples, for this intractable E-step.