Metraipolis › archive › dc_fa5b9f68ba22

Sample Complexity of Multicalibration for Multilevel Properties — arXiv:2608.04288

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04288
License (as archived)
CC0-1.0
Archived
2026-10-31T11:34:44.549Z
SHA-256 of the archived text
7bbac19c6b60589c3047c3836da6101976626ab29df352085b5cbe0ec17a76b6
Stable URL of this page
https://metraipolis.com/documento/dc_fa5b9f68ba22

How to cite

Sample Complexity of Multicalibration for Multilevel Properties — arXiv:2608.04288 — arXiv (en), https://arxiv.org/abs/2608.04288 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa5b9f68ba22 (Metraipolis archive dc_fa5b9f68ba22, sha256 7bbac19c6b60589c3047c3836da6101976626ab29df352085b5cbe0ec17a76b6)
BibTeX
@misc{dcfa5b9f68ba22,
  title = {Sample Complexity of Multicalibration for Multilevel Properties — arXiv:2608.04288},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04288},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa5b9f68ba22; sha256 7bbac19c6b60589c3047c3836da6101976626ab29df352085b5cbe0ec17a76b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04288. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Calibration requires a predictor to be unbiased after conditioning on its own predictions. Multicalibration asks for this guarantee simultaneously across a collection of groups. Many prediction tasks ask for several related features of the same conditional outcome distribution: variance is defined relative to the mean, skewness relative to both mean and variance, and conditional value at risk relative to a quantile. We study multicalibration for a sequence of $k$ properties in which each property is identifiable once the preceding properties are fixed. This framework includes Bayes pairs but does not require the properties to arise from a single loss. For every fixed $k\ge2$, we establish matching upper and lower sample-complexity bounds up to logarithmic factors under regularity conditions. Even with only polylogarithmically many binary groups, achieving multicalibration error $\varepsilon$ requires $\widetilde{\Omega}(\varepsilon^{-(k+2)})$ samples. Conversely, for any finite group family $\mathcal G$, we give a randomized learner using $O(\varepsilon^{-(k+2)}+\varepsilon^{-2}\log|\mathcal G|)$ samples. Thus the sample complexity is $\widetilde{\Theta}(\varepsilon^{-(k+2)})$ for polynomial-size group families. We instantiate the theory for three canonical examples.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Statistics Theory (math.ST); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2608.04288 — 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 2026-10-31T11:24:48.770Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).