Metraipolis › archive › dc_ff30af6f5bab

Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition — arXiv:2608.19885

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19885
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:18.810Z
SHA-256 of the archived text
8225b26b69c88e5f409cab8fdfe1385b6e41111953a6193503ba6b6bf06ef7e1
Stable URL of this page
https://metraipolis.com/documento/dc_ff30af6f5bab

How to cite

Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition — arXiv:2608.19885 — arXiv (en), https://arxiv.org/abs/2608.19885 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff30af6f5bab (Metraipolis archive dc_ff30af6f5bab, sha256 8225b26b69c88e5f409cab8fdfe1385b6e41111953a6193503ba6b6bf06ef7e1)
BibTeX
@misc{dcff30af6f5bab,
  title = {Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition — arXiv:2608.19885},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19885},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff30af6f5bab; sha256 8225b26b69c88e5f409cab8fdfe1385b6e41111953a6193503ba6b6bf06ef7e1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19885. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

After the inputs X are known, how much additional information does the label Y carry about which dataset a sample came from? That single quantity -- estimable as the difference of two discriminators' held-out cross-entropies, D_CJS = CE(Z|X) - CE(Z|X,Y) -- is exactly the part of a dataset difference that covariate shift cannot explain. We propose the Conditional Jensen-Shannon Discrepancy (CJSD): with a task indicator Z, the chain rule I(Z;X,Y) = I(Z;X) + I(Z;Y|X) splits total task discrepancy exactly into a covariate axis and a functional axis, both estimable from two ordinary classifiers, with no task-specific predictors, generative models, or bootstrap surrogates. We prove a covariate-null property (the functional axis is exactly zero under pure covariate shift, however severe), a drift-mass law (D_CJS/ln2 equals the mass of the disagreement region for deterministic labels), a one-sided misspecification-control inequality (each direction of estimation error is bounded, unconditionally, by the excess risk of a single discriminator), and a fixed-measure metrization via an identifiability lemma. Empirically, on a ten-measure battery over 202 dataset pairs (synthetic, Electricity, Covertype), only the two conditional-information estimators -- CJSD and a kNN plug-in for the same estimand -- separate concept from covariate shift with AUC 1.0; the case for CJSD is the estimator: under controlled dimensionality scaling the kNN plug-in fails from d=64 while the discriminator route holds to d=256 with a swappable classifier, and it alone yields paired confidence intervals and sequential extensions from the same learned object. The same estimator audits the conditional fidelity of synthetic-data generators that marginal and joint QA metrics pass, detects annotation-guideline changes invisible to input-space monitors, and supports null-calibrated fairness audits.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.19885 — 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 2026-10-18T11:47:43.323Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).