Loading...
Please wait, while we are loading the content...
Similar Documents
UvA-DARE ( Digital Academic Repository ) Explorations in Homeomorphic Variational Auto-Encoding
| Content Provider | Semantic Scholar |
|---|---|
| Author | Falorsi, Luca Haan, Pim De Davidson, Tim R. Cao, Nicola De Weiler, Maurice Forré, Patrick Cohen, Taco |
| Copyright Year | 2018 |
| Abstract | The manifold hypothesis states that many kinds of high-dimensional data are concentrated near a low-dimensional manifold. If the topology of this data manifold is non-trivial, a continuous encoder network cannot embed it in a one-to-one manner without creating holes of low density in the latent space. This is at odds with the Gaussian prior assumption typically made in Variational Auto-Encoders (VAEs), because the density of a Gaussian concentrates near a blob-like manifold. In this paper we investigate the use of manifoldvalued latent variables. Specifically, we focus on the important case of continuously differentiable symmetry groups (Lie groups), such as the group of 3D rotations SO(3). We show how a VAE with SO(3)-valued latent variables can be constructed, by extending the reparameterization trick to compact connected Lie groups. Our experiments show that choosing manifold-valued latent variables that match the topology of the latent data manifold, is crucial to preserve the topological structure and learn a well-behaved latent space. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | https://pure.uva.nl/ws/files/38815365/76_Explorations_in_Homeomorphic_Variational_Auto_Encoding.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
