Lifting Architectural Constraints of Injective Flows

Understand

Normalizing Flows explicitly maximize a full-dimensional likelihood on the training data.

• However, real data is typically only supported on a lower-dimensional manifold leading the model to expend significant compute on modeling noise.
• Injective Flows fix this by jointly learning a manifold and the distribution on it.
• So far, they have been limited by restrictive architectures and/or high computational cost.