← Search

Lea Zimmermann

2 accepted papers

2024

Free-form Flows: Make Any Architecture a Normalizing Flow

AISTATS 2024poster

Normalizing Flows are generative models that directly maximize the likelihood. Previously, the design of normalizing flows was largely constrained by the need for analytical invertibility. We overcome this constraint by a training procedure that uses an efficient estimator for the gradient of the ch…

2024

Lifting Architectural Constraints of Injective Flows

ICLR 2024poster

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…

Cited by 11SourcePDFScholar