Metraipolis › archive › dc_0d330c483efd

Generalizing Metropolis-Hastings for DAG Sampling — arXiv:2610.30291

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.30291
License (as archived): CC0-1.0
Archived: 2026-10-23T15:14:49.056Z
SHA-256 of the archived text: 6213e51cd35b4167900e82fb14fddd98f0600ca94d481ba505b97886b5e49750
Stable URL of this page: https://metraipolis.com/documento/dc_0d330c483efd

How to cite

Generalizing Metropolis-Hastings for DAG Sampling — arXiv:2610.30291 — arXiv (en), https://arxiv.org/abs/2610.30291 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d330c483efd (Metraipolis archive dc_0d330c483efd, sha256 6213e51cd35b4167900e82fb14fddd98f0600ca94d481ba505b97886b5e49750)

BibTeX

@misc{dc0d330c483efd,
  title = {Generalizing Metropolis-Hastings for DAG Sampling — arXiv:2610.30291},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30291},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d330c483efd; sha256 6213e51cd35b4167900e82fb14fddd98f0600ca94d481ba505b97886b5e49750},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30291. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A fundamental challenge in Bayesian network structure learning lies in efficiently approximating the posterior distribution of directed acyclic graphs (DAGs). For large, high-dimensional datasets, the task remains beyond the capabilities of current methods. This work advances Markov chain Monte Carlo algorithms by introducing novel moves that simultaneously resample the parents for multiple nodes of the DAG. At the core of these moves is duet sampling, a new generalization of the Metropolis-Hastings algorithm that selects two proposal distributions from a pool at each iteration. One is used for generating a candidate state of the Markov chain and another for evaluating the return to the current state; both are ingredients of an appropriately crafted acceptance criterion. Pairing different proposal distributions provides additional freedom and enables constructing Markov chains that mix more efficiently than their basic Metropolis-Hastings counterparts, at no additional computational cost. Experiments show that our new moves, both individually and in combination, outperform the previous state of the art, which relies on a more restrictive pool of moves. This advantage persists even when letting the previous methods leverage duet sampling to enhance their performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation (stat.CO).
Pagina del lavoro: https://arxiv.org/abs/2610.30291 — 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 2026-10-23T15:09:08.503Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).