Metraipolis › archive › dc_7eefaf502764
Sampling Interventional Distributions with Orthogonal MMD Flow — arXiv:2611.03962
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03962
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:39:24.739Z
- SHA-256 of the archived text
9a29c1e74089de52dc0f5823c8b3a0923b458bf08ac508407b733d4c629b508a- Stable URL of this page
https://metraipolis.com/documento/dc_7eefaf502764
How to cite
Sampling Interventional Distributions with Orthogonal MMD Flow — arXiv:2611.03962 — arXiv (en), https://arxiv.org/abs/2611.03962 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7eefaf502764 (Metraipolis archive dc_7eefaf502764, sha256 9a29c1e74089de52dc0f5823c8b3a0923b458bf08ac508407b733d4c629b508a)
BibTeX
@misc{dc7eefaf502764,
title = {Sampling Interventional Distributions with Orthogonal MMD Flow — arXiv:2611.03962},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03962},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7eefaf502764; sha256 9a29c1e74089de52dc0f5823c8b3a0923b458bf08ac508407b733d4c629b508a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03962. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many causal inference problems require sampling from interventional outcome distributions rather than estimating low-dimensional summaries. Existing approaches often rely on fitting generative models of the target distribution together with additional nuisance components, which can be computationally demanding for high-dimensional outcomes. We propose Interventional Maximum Mean Discrepancy Flow (IMMD-Flow), a particle-based method that instead represents the target interventional distribution through its kernel mean embedding. This kernel embedding admits a doubly robust, Neyman-orthogonal estimator with finite-sample guarantees and can be efficiently reused to sample from the interventional distribution via MMD gradient flow. IMMD-Flow accommodates both hard and soft interventions, admits theoretical guarantees for estimation and particle approximation, and extends to high-dimensional image outcomes through frozen encoders. Across image-based benchmarks, IMMD-Flow matches or improves upon state-of-the-art generative approaches while showing significant speed advantages. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.03962 — 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 2026-11-04T12:29:47.259Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).