Showing stat.MLShow all
2 papers · 1 filter
stat.ML2025
Canonical normalizing flows for manifold learning
Kyriakos Flouris, Ender Konukoglu
Manifold learning flows are a class of generative modelling techniques that assume a low-dimensional manifold description of the data. The embedding of such a manifold into the hig…
stat.ML2025
Explicit and data-Efficient Encoding via Gradient Flow
Kyriakos Flouris, Anna Volokitin, Gustav Bredell +1
The autoencoder model typically uses an encoder to map data to a lower dimensional latent space and a decoder to reconstruct it. However, relying on an encoder for inversion can le…