Metraipolis › archive › dc_dd658cbb2fe2

Online local learning for generative thermodynamic computing — arXiv:2609.15439

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.15439
License (as archived): CC0-1.0
Archived: 2026-10-16T00:15:56.384Z
SHA-256 of the archived text: 53fd76c1f7ecb701c7220871dfd0af6ea1384d79a7b58ff5d759a6e9e5f10dc6
Stable URL of this page: https://metraipolis.com/documento/dc_dd658cbb2fe2

How to cite

Online local learning for generative thermodynamic computing — arXiv:2609.15439 — arXiv (en), https://arxiv.org/abs/2609.15439 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dd658cbb2fe2 (Metraipolis archive dc_dd658cbb2fe2, sha256 53fd76c1f7ecb701c7220871dfd0af6ea1384d79a7b58ff5d759a6e9e5f10dc6)

BibTeX

@misc{dcdd658cbb2fe2,
  title = {Online local learning for generative thermodynamic computing — arXiv:2609.15439},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15439},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dd658cbb2fe2; sha256 53fd76c1f7ecb701c7220871dfd0af6ea1384d79a7b58ff5d759a6e9e5f10dc6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15439. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative thermodynamic computers turn thermal noise into structured data through Langevin dynamics. We train these systems with a local update at each integration step. The reverse-path Onsager-Machlup objective yields a coupling gradient that is a symmetric sum of local residual-state correlations. We apply this gradient immediately rather than accumulating it over a full trajectory. In digital simulations using MNIST prototypes, online and trajectory-batch training reach similar validation losses on fixed noising paths. Models trained online release less heat on average in all five independently seeded pairs, with both models' parameters held fixed during sampling. Auxiliary classifier and nearest-prototype measures change modestly, while pairwise diversity decreases. The response to noise depends strongly on where the errors enter: independent zero-mean errors in the formed updates produce little heat change over a finite range of noise amplitudes, whereas residual offset and temporal correlation have much larger effects. Storing trained couplings requires substantially less precision than resolving deterministic updates during training. Together, these results establish a local online training method and show how update timing, noise structure, and precision affect generative thermodynamic computing.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Data Analysis, Statistics and Probability (physics.data-an) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.15439 — 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 2026-10-15T23:54:14.968Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).