Metraipolis › archive › dc_ca30f967f529

Privacy for Free in Efficient Agnostic Halfspace Learning — arXiv:2611.05208

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05208
License (as archived)
CC0-1.0
Archived
2026-11-04T18:54:27.960Z
SHA-256 of the archived text
48f3ac2a5e2d5b58240fbf8ebb87c51f041a3591efd2ba66f56395b572b21016
Stable URL of this page
https://metraipolis.com/documento/dc_ca30f967f529

How to cite

Privacy for Free in Efficient Agnostic Halfspace Learning — arXiv:2611.05208 — arXiv (en), https://arxiv.org/abs/2611.05208 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca30f967f529 (Metraipolis archive dc_ca30f967f529, sha256 48f3ac2a5e2d5b58240fbf8ebb87c51f041a3591efd2ba66f56395b572b21016)
BibTeX
@misc{dcca30f967f529,
  title = {Privacy for Free in Efficient Agnostic Halfspace Learning — arXiv:2611.05208},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05208},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca30f967f529; sha256 48f3ac2a5e2d5b58240fbf8ebb87c51f041a3591efd2ba66f56395b572b21016},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05208. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We provide the first computationally efficient, differentially private algorithms for agnostically learning halfspaces. In particular, we study three different settings of agnostic learning: improper learning under Gaussian and log-concave marginals; proper learning under Gaussian marginals; and semi-agnostic learning under Gaussian marginals. In all three aforementioned settings, the added cost in the sample complexity due to privacy matches the respective non-private sample complexity, implying that we get privacy for free.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.05208 — 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 2026-11-04T18:35:37.487Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).