Metraipolis › archive › dc_a6eae2e5880a
Learning Directional Randers Geometry for Latent-Space Exploration — arXiv:2611.03675
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03675
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:28:51.289Z
- SHA-256 of the archived text
308f49fe818e973937759de4ad9a8811d20a4b5970b63b30c142aa455c784bd1- Stable URL of this page
https://metraipolis.com/documento/dc_a6eae2e5880a
How to cite
Learning Directional Randers Geometry for Latent-Space Exploration — arXiv:2611.03675 — arXiv (en), https://arxiv.org/abs/2611.03675 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6eae2e5880a (Metraipolis archive dc_a6eae2e5880a, sha256 308f49fe818e973937759de4ad9a8811d20a4b5970b63b30c142aa455c784bd1)
BibTeX
@misc{dca6eae2e5880a,
title = {Learning Directional Randers Geometry for Latent-Space Exploration — arXiv:2611.03675},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03675},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6eae2e5880a; sha256 308f49fe818e973937759de4ad9a8811d20a4b5970b63b30c142aa455c784bd1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03675. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Signal Processing (eess.SP); Differential Geometry (math.DG); Quantitative Methods (q-bio.QM). Pagina del lavoro: https://arxiv.org/abs/2611.03675 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T12:26:47.207Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).