Metraipolis › archive › dc_cbe25129b693
Partial Invariance for Classification under Structural Causal Models — arXiv:2611.02254
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02254
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:40:41.392Z
- SHA-256 of the archived text
7b670b0ccac4e5d750bdb48d36b2fd8b1924c7b05092942c2665650995ddc5eb- Stable URL of this page
https://metraipolis.com/documento/dc_cbe25129b693
How to cite
Partial Invariance for Classification under Structural Causal Models — arXiv:2611.02254 — arXiv (en), https://arxiv.org/abs/2611.02254 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cbe25129b693 (Metraipolis archive dc_cbe25129b693, sha256 7b670b0ccac4e5d750bdb48d36b2fd8b1924c7b05092942c2665650995ddc5eb)
BibTeX
@misc{dccbe25129b693,
title = {Partial Invariance for Classification under Structural Causal Models — arXiv:2611.02254},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02254},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cbe25129b693; sha256 7b670b0ccac4e5d750bdb48d36b2fd8b1924c7b05092942c2665650995ddc5eb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02254. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Making predictions in an unseen environment from data collected across multiple training environments is challenging. This challenge is particularly pronounced when the target-generating mechanism varies across environments. In this work, we introduce environment-label separation, a form of partial environmental invariance that decomposes the target conditional distribution into an environment-invariant component and a label-invariant component. We show that this partial invariance enables estimation of the target conditional distribution in an unseen environment when using labeled training data together with unlabeled test features. Within the structural causal model framework, we provide sufficient conditions for environment-label separation. Building on these conditions, we develop an algorithm, dIMP-Classifier, which jointly minimizes an estimate of the test risk and encourages invariance across environments. We further provide finite-sample guarantees that characterize the test risk in terms of deviations from invariance, estimation error, and sample complexity. Experiments on simulated data and the real-world light tunnel Causal Chamber data demonstrate that the proposed approach can perform under interventions on the target mechanism and consistently outperforms the considered standard and invariance-based baselines. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Methodology (stat.ME) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.02254 — 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 2026-11-03T18:12:54.761Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).