Metraipolis › archive › dc_659feacb281c
Formalizing the Intrinsic Dimension of Objective Landscapes by a Generalized Notion of Co-dimension — arXiv:2610.39674
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39674
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:27:15.511Z
- SHA-256 of the archived text
28bfd4556e6428405cce5d759d693a6d0a8ea53cbcf32d9624b8207920c3773f- Stable URL of this page
https://metraipolis.com/documento/dc_659feacb281c
How to cite
Formalizing the Intrinsic Dimension of Objective Landscapes by a Generalized Notion of Co-dimension — arXiv:2610.39674 — arXiv (en), https://arxiv.org/abs/2610.39674 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_659feacb281c (Metraipolis archive dc_659feacb281c, sha256 28bfd4556e6428405cce5d759d693a6d0a8ea53cbcf32d9624b8207920c3773f)
BibTeX
@misc{dc659feacb281c,
title = {Formalizing the Intrinsic Dimension of Objective Landscapes by a Generalized Notion of Co-dimension — arXiv:2610.39674},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39674},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_659feacb281c; sha256 28bfd4556e6428405cce5d759d693a6d0a8ea53cbcf32d9624b8207920c3773f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39674. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In this work, we formalize the concept of intrinsic dimension of objective landscapes introduced in Li et al. (2018), which measures the structural complexity of learning problems by training along randomly generated subspaces. We define the intrinsic dimension of a set $\Theta\subset\mathbb{R}^p$ as the minimal dimension $d_{\mathrm{int}}(\Theta)$ such that a random plane of dimension $d_{\mathrm{int}}(\Theta)$ in $\mathbb{R}^p$ intersects $\Theta$ with probability one. We show that it is a generalized notion of co-dimension that depends on the global geometry of $\Theta$. We study mathematical properties of the intrinsic dimension and develop techniques to estimate the intrinsic dimension of sets $\Theta$ that arise in learning problems. More specifically, we derive upper and/or lower bounds where $\Theta$ is the set of optimal parameters in student-teacher settings with shallow and deep ReLU networks, including finite and infinite sample cases, and with and without regularization. We discuss how our theory leads to novel types of generalization bounds, thereby showing that the intrinsic dimension is a measure of learning complexity. Our results connect techniques from seemingly different areas of machine learning research such as classification of symmetries of ReLU networks and stochastic geometry.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Metric Geometry (math.MG).
Pagina del lavoro: https://arxiv.org/abs/2610.39674 — 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 2026-11-01T02:12:44.309Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).