Metraipolis › archive › dc_5fdc7fde5a2d

Neural Transport Nested Sampling — arXiv:2609.29413

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29413
License (as archived)
CC0-1.0
Archived
2026-10-08T05:25:59.932Z
SHA-256 of the archived text
e28918ce99ffa30ad1a749b2168b06e1c9d58a15b853cd726dd852de88a1d8c5
Stable URL of this page
https://metraipolis.com/documento/dc_5fdc7fde5a2d

How to cite

Neural Transport Nested Sampling — arXiv:2609.29413 — arXiv (en), https://arxiv.org/abs/2609.29413 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5fdc7fde5a2d (Metraipolis archive dc_5fdc7fde5a2d, sha256 e28918ce99ffa30ad1a749b2168b06e1c9d58a15b853cd726dd852de88a1d8c5)
BibTeX
@misc{dc5fdc7fde5a2d,
  title = {Neural Transport Nested Sampling — arXiv:2609.29413},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29413},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5fdc7fde5a2d; sha256 e28918ce99ffa30ad1a749b2168b06e1c9d58a15b853cd726dd852de88a1d8c5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29413. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sampling from Boltzmann distributions of molecular systems is an inference problem that has seen significant recent developments fuelled by advances in neural density estimation. We develop a novel sampling algorithm, Neural Transport Nested Sampling (NTNS), which combines the classical strengths of nested sampling with modern neural flow-based methods. NTNS uses a flow matching velocity as the drift in a Metropolis--Hastings corrected Langevin kernel inside a nested sampling outer loop, requiring only evaluations of the target energy function and providing scalable estimation of the full partition function of high-dimensional particle systems. We benchmark NTNS on challenging molecular sampling benchmarks, scaling up to Lennard--Jones clusters of 55 interacting particles, where it reduces both interatomic distance and energy Wasserstein errors to reference MCMC by over an order of magnitude relative to the strongest neural baselines at lower wall-clock cost. To our knowledge, NTNS is also the first neural sampler to return a calibrated, temperature resolved partition function estimate at this scale, recovering the phase structure across temperature from a single run.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.29413 — 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 2026-10-08T04:50:39.395Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).