Metraipolis › archive › dc_b2e2a4a00253

Boosting and the Expressive Power of Simple Weak Learners via the $γ$-VC Dimension — arXiv:2610.10383

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10383
License (as archived)
CC0-1.0
Archived
2026-10-08T12:36:26.007Z
SHA-256 of the archived text
4c956e6e149934bbeea6d6f49c2b81117d31e63d789d1fbd34a39a2e84992106
Stable URL of this page
https://metraipolis.com/documento/dc_b2e2a4a00253

How to cite

Boosting and the Expressive Power of Simple Weak Learners via the $γ$-VC Dimension — arXiv:2610.10383 — arXiv (en), https://arxiv.org/abs/2610.10383 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b2e2a4a00253 (Metraipolis archive dc_b2e2a4a00253, sha256 4c956e6e149934bbeea6d6f49c2b81117d31e63d789d1fbd34a39a2e84992106)
BibTeX
@misc{dcb2e2a4a00253,
  title = {Boosting and the Expressive Power of Simple Weak Learners via the $γ$-VC Dimension — arXiv:2610.10383},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10383},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b2e2a4a00253; sha256 4c956e6e149934bbeea6d6f49c2b81117d31e63d789d1fbd34a39a2e84992106},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10383. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Boosting converts weak hypotheses with a small edge over random guessing into highly accurate predictors, but the expressive power of the resulting classifier can depend strongly on the structure of the base class. We study this phenomenon through the $\gamma$-VC dimension introduced by Alon et al. (STOC 2021). Our first result shows that this parameter characterizes the sample complexity for weak-to-strong learning up to a constant factor scaling in $\gamma$. We then sharpen the general relationship between the classic VC dimension and the $\gamma$-VC dimension. Finally, we also give improved upper and lower bounds on the $\gamma$-VC dimension for the fundamental concept classes of decision stumps and axis-parallel rectangles in $\mathbb{R}^d$.

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/2610.10383 — 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 2026-10-08T12:14:15.343Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).