Skip to content

Latest commit

 

History

History
49 lines (49 loc) · 1.77 KB

2021-03-18-arvanitidis21a.md

File metadata and controls

49 lines (49 loc) · 1.77 KB
title abstract layout series publisher issn id month tex_title firstpage lastpage page order cycles bibtex_author author date address container-title volume genre issued pdf extras
Geometrically Enriched Latent Spaces
A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space. Instead, we consider the ambient space to be a Riemannian manifold, which allows for encoding domain knowledge through the associated Riemannian metric. Shortest paths can then be defined accordingly in the latent space to both follow the learned manifold and respect the ambient geometry. Through careful design of the ambient metric we can ensure that shortest paths are well-behaved even for deterministic generators that otherwise would exhibit a misleading bias. Experimentally we show that our approach improves the interpretability and the functionality of learned representations both using stochastic and deterministic generators.
inproceedings
Proceedings of Machine Learning Research
PMLR
2640-3498
arvanitidis21a
0
Geometrically Enriched Latent Spaces
631
639
631-639
631
false
Arvanitidis, Georgios and Hauberg, Soren and Sch{\"o}lkopf, Bernhard
given family
Georgios
Arvanitidis
given family
Soren
Hauberg
given family
Bernhard
Schölkopf
2021-03-18
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics
130
inproceedings
date-parts
2021
3
18