Search Results for author:
Found 5 papers, 5 papers with code
Learning Distributions on Manifolds with Free-form Flows
Many real world data, particularly in the natural sciences and computer vision, lie on known Riemannian manifolds such as spheres, tori or the group of rotation matrices.
Free-form Flows: Make Any Architecture a Normalizing Flow
Normalizing Flows are generative models that directly maximize the likelihood.
Lifting Architectural Constraints of Injective Flows
Normalizing Flows explicitly maximize a full-dimensional likelihood on the training data.
Better Latent Spaces for Better Autoencoders
In particular, the Dirichlet setup solves the problem and improves both the performance and the interpretability of the networks.
Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)
Furthermore, the recovered informative latent variables will be in one-to-one correspondence with the true latent variables of the generating process, up to a trivial component-wise transformation.
