Metraipolis › archive › dc_cbfa895f60c6
The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective — arXiv:2610.07131
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07131
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:40:53.535Z
- SHA-256 of the archived text
9151171bb25d294045b35b286e255e9b2b5a6545c7e1136f191d3fae9d9da96f- Stable URL of this page
https://metraipolis.com/documento/dc_cbfa895f60c6
How to cite
The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective — arXiv:2610.07131 — arXiv (en), https://arxiv.org/abs/2610.07131 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbfa895f60c6 (Metraipolis archive dc_cbfa895f60c6, sha256 9151171bb25d294045b35b286e255e9b2b5a6545c7e1136f191d3fae9d9da96f)
BibTeX
@misc{dccbfa895f60c6,
title = {The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Perspective — arXiv:2610.07131},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07131},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbfa895f60c6; sha256 9151171bb25d294045b35b286e255e9b2b5a6545c7e1136f191d3fae9d9da96f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07131. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the implicit bias of Riemannian gradient flow for hyperbolic multiclass classification with fixed class prototypes in hyperbolic space $\mathbb{H}^n$. Our framework accommodates general permutation invariant relative margin (PERM) losses, a class that includes cross entropy and other standard multiclass losses. Our analysis is based on a decomposition: at large radius, the distance to each prototype splits into a radial term and a direction-dependent term described by the Busemann function. This yields two main results. First, we prove a radial dichotomy: the sign of a drift coefficient $\mu$ determines whether the radius is pushed toward the ideal boundary or back toward the interior; if the positive drift persists, then $r(t)=\frac{1}{2}\log t+O(1)$, while persistent negative drift returns the trajectory to the large-radius threshold in finite time. Second, we show that the boundary direction converges to a critical point of the Busemann risk on $\partial\mathbb{H}^n$. These results provide a rigorous asymptotic perspective on two phenomena we refer to as boundary saturation and near-boundary clustering in hyperbolic representation learning.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.07131 — 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 2026-10-07T11:19:24.731Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).