TY  - EJOUR
AU  - Cramer, Eike
AU  - Rauh, Felix
AU  - Mitsos, Alexander
AU  - Tempone, Raúl
AU  - Dahmen, Manuel
TI  - Nonlinear Isometric Manifold Learning for Injective Normalizing Flows
PB  - arXiv
M1  - FZJ-2023-00760
PY  - 2022
AB  - To model manifold data using normalizing flows, we propose to employ the isometric autoencoder to design nonlinear encodings with explicit inverses. The isometry allows us to separate manifold learning and density estimation and train both parts to high accuracy. Applied to the MNIST data set, the combined approach generates high-quality images.
KW  - Machine Learning (cs.LG) (Other)
KW  - FOS: Computer and information sciences (Other)
LB  - PUB:(DE-HGF)25
DO  - DOI:10.48550/ARXIV.2203.03934
UR  - https://juser.fz-juelich.de/record/917558
ER  -