Metraipolis › archive › dc_01468f45b76f
Dimension-Free Scaling Laws for Size Generalization: An Exponential Separation — arXiv:2610.19279
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19279
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:15:22.522Z
- SHA-256 of the archived text
37591478e0dd9aa18fcbecfa3496af2e29947af6e04c761c81b4f0dd305520d3- Stable URL of this page
https://metraipolis.com/documento/dc_01468f45b76f
How to cite
Dimension-Free Scaling Laws for Size Generalization: An Exponential Separation — arXiv:2610.19279 — arXiv (en), https://arxiv.org/abs/2610.19279 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01468f45b76f (Metraipolis archive dc_01468f45b76f, sha256 37591478e0dd9aa18fcbecfa3496af2e29947af6e04c761c81b4f0dd305520d3)
BibTeX
@misc{dc01468f45b76f,
title = {Dimension-Free Scaling Laws for Size Generalization: An Exponential Separation — arXiv:2610.19279},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19279},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01468f45b76f; sha256 37591478e0dd9aa18fcbecfa3496af2e29947af6e04c761c81b4f0dd305520d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19279. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern machine learning models increasingly operate on variable-size structured data, such as sets and graphs. A central requirement is \emph{size generalization}: the ability of a model trained on inputs of one size to generalize to inputs of a different, potentially much larger, size. Classical statistical learning theory, however, primarily considers fixed input domains, and its guarantees often deteriorate with input dimension. Although extensive work has established when models on sets and graphs can be transferred across input sizes, such results do not characterize the statistical cost of doing so: the sample complexity of size generalization, and its relationship to classical in-domain learning, remain largely unknown. We develop a statistical learning theory of size generalization and establish a sharp exponential separation in sample complexity. Letting $n$ denote the number of training samples, we show that polynomial source decay is insufficient for efficient size generalization: while it yields error $n^{-\Theta(1)}$ and hence polynomial sample complexity for in-domain learning, size-generalization error decays only as $(\log n)^{-\Theta(1)}$, yielding an exponential separation. Thus, polynomial in-domain sample complexity can become exponential across sizes. We then identify an exponential source condition under which size generalization achieves error $n^{-\Theta(1)}$, recovering polynomial sample complexity. These guarantees are independent of input dimension and depend only on the number of training samples, yielding dimension-free scaling laws. We also provide matching minimax lower bounds, establishing optimality. To our knowledge, this work provides the first dimension-free minimax theory of size generalization and a rigorous characterization of when, and at what statistical cost, learning can transfer across input sizes.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.19279 — 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 2026-10-15T13:53:35.560Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).