Metraipolis › archive › dc_ac7cf061fa8e

Bagging Robustly Learns VC Classes with Linear Sample Complexity — arXiv:2608.13514

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13514
License (as archived)
CC0-1.0
Archived
2026-10-19T04:27:58.729Z
SHA-256 of the archived text
8756a3391fb795749bacd6ea6e02a7df3547030c2a87f3944ef4649afb0fd095
Stable URL of this page
https://metraipolis.com/documento/dc_ac7cf061fa8e

How to cite

Bagging Robustly Learns VC Classes with Linear Sample Complexity — arXiv:2608.13514 — arXiv (en), https://arxiv.org/abs/2608.13514 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac7cf061fa8e (Metraipolis archive dc_ac7cf061fa8e, sha256 8756a3391fb795749bacd6ea6e02a7df3547030c2a87f3944ef4649afb0fd095)
BibTeX
@misc{dcac7cf061fa8e,
  title = {Bagging Robustly Learns VC Classes with Linear Sample Complexity — arXiv:2608.13514},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13514},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac7cf061fa8e; sha256 8756a3391fb795749bacd6ea6e02a7df3547030c2a87f3944ef4649afb0fd095},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13514. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample complexity linear in the VC dimension $d$, providing an exponential improvement over the previous upper bound of Montasser, Hanneke, and Srebro (2019). Remarkably, this result is achieved with a simple improper algorithm that combines the classic heuristic bagging (bootstrap aggregation) of Breiman (1996) with robust empirical risk minimization (RERM). Our algorithm computes RERMs on $O(d^\star)$ independent bootstrap samples and outputs their majority vote, where $d^\star$ denotes the dual VC dimension. We complement this result with a lower bound showing that this is unavoidable: in general, any learner in this oracle model requires $\Omega(d^\star)$ calls to an RERM oracle, even when given arbitrarily many training examples.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Data Structures and Algorithms (cs.DS); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.13514 — 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 2026-10-19T04:20:35.919Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).