Metraipolis › archive › dc_e8843deba2b5
Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching — arXiv:2608.28840
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.28840
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:32:28.991Z
- SHA-256 of the archived text
9b23111adb234454d9a8bcb53d87dbdf49c65b94c43837730ead0e1bd45c500a- Stable URL of this page
https://metraipolis.com/documento/dc_e8843deba2b5
How to cite
Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching — arXiv:2608.28840 — arXiv (en), https://arxiv.org/abs/2608.28840 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8843deba2b5 (Metraipolis archive dc_e8843deba2b5, sha256 9b23111adb234454d9a8bcb53d87dbdf49c65b94c43837730ead0e1bd45c500a)
BibTeX
@misc{dce8843deba2b5,
title = {Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching — arXiv:2608.28840},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.28840},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8843deba2b5; sha256 9b23111adb234454d9a8bcb53d87dbdf49c65b94c43837730ead0e1bd45c500a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28840. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Independently trained neural networks tend to encode the same data with similar latent geometries. These latent geometries are not directly compatible, yet they can be nearly the same up to some class of transformations. While there exists many methods for alignment between different latent spaces, it is typically done using a set of shared sample correspondences, known as anchors. This leaves a fundamental question: are the geometric signatures of different latent spaces representing similar data sufficient to recover an alignment between them? To that end, we introduce HGA (Hyperspherical Gaussian Alignment), a method that directly optimizes a transformation between two latent spaces by maximizing a geometric measure of "fit" between them. Since it is driven by the geometry of the latent spaces rather than paired data, HGA can operate in both an unsupervised and weakly supervised regime. On tasks such as model stitching or multilingual word embedding correspondence recovery, HGA manages to match supervised results with minimal or no supervision. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.28840 — 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 2026-10-17T08:13:26.708Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).