Metraipolis › archive › dc_6a017d3fca32

Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference — arXiv:2610.39305

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39305
License (as archived)
CC0-1.0
Archived
2026-10-31T06:13:10.574Z
SHA-256 of the archived text
7c77bbed9c79ea70b36586d9c4dc8ac10631e387b38779e988edd22867f0ab51
Stable URL of this page
https://metraipolis.com/documento/dc_6a017d3fca32

How to cite

Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference — arXiv:2610.39305 — arXiv (en), https://arxiv.org/abs/2610.39305 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6a017d3fca32 (Metraipolis archive dc_6a017d3fca32, sha256 7c77bbed9c79ea70b36586d9c4dc8ac10631e387b38779e988edd22867f0ab51)
BibTeX
@misc{dc6a017d3fca32,
  title = {Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference — arXiv:2610.39305},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39305},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6a017d3fca32; sha256 7c77bbed9c79ea70b36586d9c4dc8ac10631e387b38779e988edd22867f0ab51},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39305. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Probabilistic graphical models (PGMs) compactly encode structured joint distributions, but Most Probable Explanation (MPE), which finds the highest-probability assignment to unobserved variables, remains computationally intractable in large, densely structured models. Anytime systematic search, such as branch-and-bound (B&B), is a popular approach, but its efficiency depends on tight admissible upper bounds that are often prohibitively expensive to compute using classical methods like Mini-Bucket Elimination (MBE). We introduce Learning to Bound (L2B), a data-driven framework that amortizes bound computation cost by training a neural predictor. L2B targets two key properties required for effective search bounds: admissibility, which is achieved via statistical calibration techniques, and progressive tightening as evidence accumulates, which is enforced through structural architectural constraints that ensure monotonicity by construction. Across challenging benchmarks, L2B delivers tighter, monotonic bounds at orders-of-magnitude lower cost on every PGM family, and yields measurable improvements when integrated with branch-and-bound on high-treewidth instances.

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).
Pagina del lavoro: https://arxiv.org/abs/2610.39305 — 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 2026-10-31T06:07:08.707Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).