Metraipolis › archive › dc_61a5caaf595b
Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation — arXiv:2609.02196
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.02196
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T03:37:22.974Z
- SHA-256 of the archived text
31f0b2ac85d2ed335a99c544dfadade5473004cb6ea7b419cd473be0d720a37e- Stable URL of this page
https://metraipolis.com/documento/dc_61a5caaf595b
How to cite
Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation — arXiv:2609.02196 — arXiv (en), https://arxiv.org/abs/2609.02196 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_61a5caaf595b (Metraipolis archive dc_61a5caaf595b, sha256 31f0b2ac85d2ed335a99c544dfadade5473004cb6ea7b419cd473be0d720a37e)
BibTeX
@misc{dc61a5caaf595b,
title = {Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation — arXiv:2609.02196},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.02196},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_61a5caaf595b; sha256 31f0b2ac85d2ed335a99c544dfadade5473004cb6ea7b419cd473be0d720a37e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02196. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative modeling directly on geometric manifolds can avoid errors introduced by flattening non-Euclidean data, repeated ambient projection, and coordinate inconsistency in Euclidean representations. Schrodinger bridges provide a probabilistic generative framework for entropy-regularized transport between prescribed endpoint distributions. We study Schrodinger bridges for kinetic dynamics on Lie group manifolds with state X_t = (g_t, xi_t) in G x g, allowing endpoint observations to constrain only the variables that are actually measured. In particular, the entropy projection determines the conditional law of the unobserved endpoint velocities. For the same observed endpoint bridge, we develop two computational realizations: Wrapped-Kernel Bridge Calibration (WKBC) uses an explicit periodized kinetic kernel on compact Abelian groups, whereas Reciprocal Conditional-Control Bridge Matching (RCCBM) handles compact non-Abelian groups through two-sided endpoint calibration and mollified conditional-control matching. The canonical teacher-mixture path law is itself a Markov reciprocal law, so forward generation uses a calibrated initial law and one learned Doob controller. Moreover, we establish a modular error bound in the bounded-Lipschitz path metric that provides a clean separation of errors due to endpoints, control regression, initialization, discretization, and related approximations. Experiments on multiple Lie group manifold datasets validate the feasibility and consistency of our proposed method, covering protein and RNA torsions, SO(3), U(n), and the Protein Conformational Transition Pathway Generation task using mdCATH trajectories in a compact reduced representation. The source code is publicly available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI). Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.02196 — 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 2026-10-17T03:13:12.516Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).