Learning Directional Randers Geometry for Latent-Space Exploration
Paper · https://arxiv.org/abs/2611.03675
arXiv:2611.03675v1 Announce Type: new Abstract: Deep neural networks extract powerful latent representations from images, enabling fast and efficient downstream analysis. However, these latent spaces lack explicit geometric structure, leading to possibly poor interpolation fidelity and misleading extrapolation. Latent interpolation techniques assume symmetric transition costs which are often not the case for real world data. Their symmetric nature cannot capture directional processes, such as disease progression, where certain transitions are impossible (e.g. tumor growth dynamics or cognitive improvement in Alzheimer's disease). Although Riemannian metrics extend Euclidean geometry by incorporating curvature, they remain symmetric. We show that understanding asymmetry and not curvature alone directly addresses these problems. To do so we propose a new Finsler-Randers metric learning framework. It incorporates direction-dependent distances, thus enabling the computation of trajectories respecting monotonic sequential constraints. We demonstrate its potential for interpolation and extrapolation on controlled cross-sectional datasets.
First seen by Oriel on .
AI summary
The paper proposes a Finsler-Randers metric learning framework that gives neural latent spaces direction-dependent geometry for trajectories constrained by asymmetric, monotonic real-world processes.
- Conventional latent interpolation assumes symmetric transition costs, which can misrepresent irreversible processes such as tumor growth or cognitive improvement in Alzheimer's disease.
- Unlike symmetric Euclidean and Riemannian metrics, the proposed framework models direction-dependent distances rather than relying on curvature alone.
- The method computes trajectories that respect monotonic sequential constraints and is demonstrated for interpolation and extrapolation on controlled cross-sectional datasets.
#latent spaces #finsler geometry #metric learning #deep learning
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| arXiv AI Papers | oai:arXiv.org:2611.03675v1 | https://arxiv.org/abs/2611.03675 Read discussion |