Metraipolis › archive › dc_cda3e9676de2

Integral Probability Boundaries — arXiv:2610.38036

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38036
License (as archived)
CC0-1.0
Archived
2026-11-01T02:23:22.640Z
SHA-256 of the archived text
1d4bc43fc8252758c24a4b924af164e4f22451ba99c34ed53f4993722c0e0ead
Stable URL of this page
https://metraipolis.com/documento/dc_cda3e9676de2

How to cite

Integral Probability Boundaries — arXiv:2610.38036 — arXiv (en), https://arxiv.org/abs/2610.38036 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cda3e9676de2 (Metraipolis archive dc_cda3e9676de2, sha256 1d4bc43fc8252758c24a4b924af164e4f22451ba99c34ed53f4993722c0e0ead)
BibTeX
@misc{dccda3e9676de2,
  title = {Integral Probability Boundaries — arXiv:2610.38036},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38036},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cda3e9676de2; sha256 1d4bc43fc8252758c24a4b924af164e4f22451ba99c34ed53f4993722c0e0ead},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38036. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Bounds based on Integral Probability Metrics (IPMs) are ubiquitous in machine learning and statistics, appearing, e.g., in generalization, alignment, fairness, and privacy. IPMs reduce the discrepancy between two distributions to a single worst-case gap between expectations. This compression is costly: for rare events, safety failures, or under-represented groups, IPM-based bounds are loose or vacuous. We introduce a non-linear generalization of IPMs, which we term Integral Probability Boundaries (IPBs). Unlike IPMs, IPBs provide bounds that are tight at the extremes. We derive their basic properties and present algorithms for estimating them in practically relevant settings. We demonstrate the usage of IPBs in both theoretical and practical applications for alignment, judge-free performance estimation, and fairness, where they enable us to obtain sharp bounds on performance and fairness gaps, e.g., 15 p.p. more precise estimates on fairness gaps for rare groups in a realistic generative modeling task, compared to the state of the art.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Information Theory (cs.IT); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.38036 — 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 2026-11-01T02:12:44.098Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).