Metraipolis › archive › dc_9ebb38df60ab
How Many Samples Are Enough for Learning Across Domains? — arXiv:2609.39336
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39336
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:46:05.104Z
- SHA-256 of the archived text
1dd6e0928b67426edaec82a99c05df41aa50b3d85f4234ad86eb1a0184f4d9c2- Stable URL of this page
https://metraipolis.com/documento/dc_9ebb38df60ab
How to cite
How Many Samples Are Enough for Learning Across Domains? — arXiv:2609.39336 — arXiv (en), https://arxiv.org/abs/2609.39336 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ebb38df60ab (Metraipolis archive dc_9ebb38df60ab, sha256 1dd6e0928b67426edaec82a99c05df41aa50b3d85f4234ad86eb1a0184f4d9c2)
BibTeX
@misc{dc9ebb38df60ab,
title = {How Many Samples Are Enough for Learning Across Domains? — arXiv:2609.39336},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39336},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ebb38df60ab; sha256 1dd6e0928b67426edaec82a99c05df41aa50b3d85f4234ad86eb1a0184f4d9c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39336. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Understanding the fundamental mechanisms of learning is essential for designing systems with strong generalization. Recent studies have shown that increasing the number of training domains, or enlarging the distribution shift among them, improves generalization when each domain contains sufficiently many data samples. However, the conditions under which the data samples can be considered sufficient remain unexplored. In this work, we fill this gap by establishing criteria for per-domain sample requirements based on the presented learning bounds. These criteria not only reveal an inverse linear scaling law between the number of training domains and the number of samples required per domain, but also explain the fundamental rationale behind the assumption of data sufficiency, thereby providing theoretical guidance for assessing the adequacy of existing datasets and constructing datasets. This differs from classical learning theory, as the number of samples required is highly dependent on the number of training domains. Additionally, we prove the close relationship between in-domain learning and out-of-domain generalization through the presented generalization bounds, and lastly discuss some key arguments. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.39336 — 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 2026-10-07T13:18:10.363Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).