Metraipolis › archive › dc_c02ce26be97e

Conformal Prediction under Exponential-Tilt Joint Shift — arXiv:2609.30886

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30886
License (as archived)
CC0-1.0
Archived
2026-10-08T02:19:14.847Z
SHA-256 of the archived text
4f2c5cae9a650bfb264f47d6c3b55f61611c7bfe5a8659d3de513a9ac4168390
Stable URL of this page
https://metraipolis.com/documento/dc_c02ce26be97e

How to cite

Conformal Prediction under Exponential-Tilt Joint Shift — arXiv:2609.30886 — arXiv (en), https://arxiv.org/abs/2609.30886 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c02ce26be97e (Metraipolis archive dc_c02ce26be97e, sha256 4f2c5cae9a650bfb264f47d6c3b55f61611c7bfe5a8659d3de513a9ac4168390)
BibTeX
@misc{dcc02ce26be97e,
  title = {Conformal Prediction under Exponential-Tilt Joint Shift — arXiv:2609.30886},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30886},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c02ce26be97e; sha256 4f2c5cae9a650bfb264f47d6c3b55f61611c7bfe5a8659d3de513a9ac4168390},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30886. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Conformal prediction can lose coverage when the data distribution changes after deployment. We study adaptation using labeled source data and unlabeled target inputs, allowing both the input distribution and its relationship with outcomes to change. We use Exponential Tilt Reweighting Alignment (ExTRA), introduced for classification by Maity et al. (2023), to estimate structured distribution shifts. We compare using its estimated weights in conformal calibration with additionally tilting the source predictive distribution. Shared learned predictors, estimated weights, calibration samples, and test observations isolate the effect of tilting. Existing theory gives both procedures target coverage with true weights and a common coverage bound with estimated weights. Identification calculations and an analysis of how scoring interacts with weight estimation error help explain why their performance can nevertheless differ. In a synthetic regression setting where the assumed models match the data-generating process and target inputs are informative about the shift, tilting reduces mean set length by about $30\%$ relative to weighting alone, with both methods attaining coverage near nominal. Tilting can instead cause substantial coverage losses in synthetic classification and in regression when target inputs provide little information about the response shift. Real-data experiments also show no consistent benefit. Good coverage from weighted calibration alone does not ensure that adding predictive tilting will preserve coverage. Deciding when to apply this additional adjustment using only source labels and target inputs remains an open problem.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2609.30886 — 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 2026-10-08T01:43:06.801Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).