Metraipolis › archive › dc_4e4d4e4b4ea1

Nonlocal Transition Kernel for Efficient Learning of Restricted Boltzmann Machines — arXiv:2608.17450

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.17450
License (as archived): CC0-1.0
Archived: 2026-10-18T14:49:03.946Z
SHA-256 of the archived text: 9acfe1f17dc5cd928d2c8dfd17ffc965676d841a0677e3f4bc7c0fbcfaffbaba
Stable URL of this page: https://metraipolis.com/documento/dc_4e4d4e4b4ea1

How to cite

Nonlocal Transition Kernel for Efficient Learning of Restricted Boltzmann Machines — arXiv:2608.17450 — arXiv (en), https://arxiv.org/abs/2608.17450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e4d4e4b4ea1 (Metraipolis archive dc_4e4d4e4b4ea1, sha256 9acfe1f17dc5cd928d2c8dfd17ffc965676d841a0677e3f4bc7c0fbcfaffbaba)

BibTeX

@misc{dc4e4d4e4b4ea1,
  title = {Nonlocal Transition Kernel for Efficient Learning of Restricted Boltzmann Machines — arXiv:2608.17450},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17450},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e4d4e4b4ea1; sha256 9acfe1f17dc5cd928d2c8dfd17ffc965676d841a0677e3f4bc7c0fbcfaffbaba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning restricted Boltzmann machines (RBMs) is computationally challenging because it requires expectations whose exact evaluation is generally intractable. The expectations are typically evaluated using a sampling approximation based on blocked Gibbs sampling (BGS), which is a local Markov chain Monte Carlo transition kernel. However, the locality of BGS can lead to poor sampling quality when the RBM has high energy barriers, thereby degrading learning performance. Deep tempering (DT), which performs parallel tempering over a sequence of learnable RBMs including the training RBM, alleviates this locality issue. However, DT algorithmically requires multiple steps to move through the RBM sequence to achieve a nonlocal transition. In this paper, we propose a transition kernel defined over the RBM sequence used in DT. The proposed kernel has a round-trip structure over the sequence, enabling nonlocal moves within a single transition while leaving the RBM sequence invariant. Numerical experiments show that the proposed kernel performs nonlocal transitions more frequently and achieves higher sampling quality with fewer transitions than BGS and DT. We further verify that learning based on the proposed kernel is more stable and mitigates the training failures observed with BGS- and DT-based learning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Disordered Systems and Neural Networks (cond-mat.dis-nn); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.17450 — 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 2026-10-18T14:47:59.460Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).