Metraipolis › archive › dc_4044116e60bf
Singularity-Induced Local Complexity for High-Dimensional Learning Models — arXiv:2611.02428
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02428
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:37:21.402Z
- SHA-256 of the archived text
c5e84b858409717cd9505b62ed5b26105ff02a05dc8c5b6b06b4ead45c7d5b59- Stable URL of this page
https://metraipolis.com/documento/dc_4044116e60bf
How to cite
Singularity-Induced Local Complexity for High-Dimensional Learning Models — arXiv:2611.02428 — arXiv (en), https://arxiv.org/abs/2611.02428 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4044116e60bf (Metraipolis archive dc_4044116e60bf, sha256 c5e84b858409717cd9505b62ed5b26105ff02a05dc8c5b6b06b4ead45c7d5b59)
BibTeX
@misc{dc4044116e60bf,
title = {Singularity-Induced Local Complexity for High-Dimensional Learning Models — arXiv:2611.02428},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02428},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4044116e60bf; sha256 c5e84b858409717cd9505b62ed5b26105ff02a05dc8c5b6b06b4ead45c7d5b59},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02428. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many overparameterized models that have achieved remarkable success are singular models. That is, the set of optimal parameters consists of multiple points, or the Hessian of the generalization error at such parameters is degenerate, reflecting redundancy in the model parametrization. Therefore, understanding the effective dimension and intrinsic model complexity, beyond the apparent dimension of the parameter space, is essential for studying the generalization ability of such overparameterized models. In this work, we focus on the real log canonical threshold (RLCT) and its localized counterpart, the local RLCT, which are fundamental quantities for characterizing the generalization of singular models. We clarify the theoretical relationship between the local RLCT and existing two key metrics related to generalization under some localization assumption: (I) the rank of the Hessian matrix of the generalization error and (II) the covering number of a family of loss functions. This result provides novel insights into effective dimension and intrinsic complexity of overparameterized models. 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/2611.02428 — 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 2026-11-03T18:12:54.570Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).