Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912264598061056 |
|---|---|
| author | Rozo, Leonel González-Duque, Miguel Jaquier, Noémie Hauberg, Søren |
| author_facet | Rozo, Leonel González-Duque, Miguel Jaquier, Noémie Hauberg, Søren |
| contents | Latent variable models are powerful tools for learning low-dimensional manifolds from high-dimensional data. However, when dealing with constrained data such as unit-norm vectors or symmetric positive-definite matrices, existing approaches ignore the underlying geometric constraints or fail to provide meaningful metrics in the latent space. To address these limitations, we propose to learn Riemannian latent representations of such geometric data. To do so, we estimate the pullback metric induced by a Wrapped Gaussian Process Latent Variable Model, which explicitly accounts for the data geometry. This enables us to define geometry-aware notions of distance and shortest paths in the latent space, while ensuring that our model only assigns probability mass to the data manifold. This generalizes previous work and allows us to handle complex tasks in various domains, including robot motion synthesis and analysis of brain connectomes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05540 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data Rozo, Leonel González-Duque, Miguel Jaquier, Noémie Hauberg, Søren Machine Learning Robotics Latent variable models are powerful tools for learning low-dimensional manifolds from high-dimensional data. However, when dealing with constrained data such as unit-norm vectors or symmetric positive-definite matrices, existing approaches ignore the underlying geometric constraints or fail to provide meaningful metrics in the latent space. To address these limitations, we propose to learn Riemannian latent representations of such geometric data. To do so, we estimate the pullback metric induced by a Wrapped Gaussian Process Latent Variable Model, which explicitly accounts for the data geometry. This enables us to define geometry-aware notions of distance and shortest paths in the latent space, while ensuring that our model only assigns probability mass to the data manifold. This generalizes previous work and allows us to handle complex tasks in various domains, including robot motion synthesis and analysis of brain connectomes. |
| title | Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2503.05540 |