Deep Generative Models: Four Ways to Make Complex Distributions Learnable

Automated excerpt

An Autoregressive Model factorizes a joint distribution into conditional distributions. If This is the Cross-Entropy term between the data distribution and the model distribution. Saying that a Flow-based Model models the data distribution does not mean the learned distribution becomes identical to the true data distribution.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.