Metraipolis › archive › dc_392afa9bf43f

Structure-agnostic Causal Representation Learning — arXiv:2610.00968

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00968
License (as archived)
CC0-1.0
Archived
2026-10-06T12:12:05.765Z
SHA-256 of the archived text
c413074a10bbf68f2e0f1c225fc69187594a25818a7f152e44af53fea55e460f
Stable URL of this page
https://metraipolis.com/documento/dc_392afa9bf43f

How to cite

Structure-agnostic Causal Representation Learning — arXiv:2610.00968 — arXiv (en), https://arxiv.org/abs/2610.00968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_392afa9bf43f (Metraipolis archive dc_392afa9bf43f, sha256 c413074a10bbf68f2e0f1c225fc69187594a25818a7f152e44af53fea55e460f)
BibTeX
@misc{dc392afa9bf43f,
  title = {Structure-agnostic Causal Representation Learning — arXiv:2610.00968},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00968},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_392afa9bf43f; sha256 c413074a10bbf68f2e0f1c225fc69187594a25818a7f152e44af53fea55e460f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Causal representation learning aims to discover robust features by exploiting the causal structure underlying data generation. Existing methods require specifying the causal structure a priori, yet different structures demand fundamentally incompatible invariance constraints, and misspecification leads to representations that discard predictive information. We introduce SaCRL, a framework that jointly identifies the causal structure and learns the corresponding invariant representation without prior structural knowledge. Our approach formulates structure selection as a soft optimization over candidate invariances using HSIC-based violation metrics, with adaptive weights that automatically concentrate on the achievable structure. We provide theoretical guarantees for structure identification, including under random-feature approximation, invariance satisfaction, and out-of-distribution generalization. Empirically, SaCRL recovers the true structure on synthetic and semi-synthetic Bayesian-network benchmarks, outperforms fixed-invariance baselines on Colored MNIST, achieves state-of-the-art accuracy on three DomainBed benchmarks (PACS, VLCS, OfficeHome), and degrades gracefully under structural misspecification and limited environment diversity. Code is available at: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.00968 — 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 2026-10-06T10:21:28.137Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).