Metraipolis › archive › dc_32ee0efd7045

Entropy Estimates from Stochastic Interpolants — arXiv:2609.18093

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18093
License (as archived)
CC0-1.0
Archived
2026-10-15T17:54:08.279Z
SHA-256 of the archived text
98d31c8ccba4c67ecd982a5bc28057470bfa9f0185f9eb0b70ab31a337244544
Stable URL of this page
https://metraipolis.com/documento/dc_32ee0efd7045

How to cite

Entropy Estimates from Stochastic Interpolants — arXiv:2609.18093 — arXiv (en), https://arxiv.org/abs/2609.18093 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_32ee0efd7045 (Metraipolis archive dc_32ee0efd7045, sha256 98d31c8ccba4c67ecd982a5bc28057470bfa9f0185f9eb0b70ab31a337244544)
BibTeX
@misc{dc32ee0efd7045,
  title = {Entropy Estimates from Stochastic Interpolants — arXiv:2609.18093},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18093},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_32ee0efd7045; sha256 98d31c8ccba4c67ecd982a5bc28057470bfa9f0185f9eb0b70ab31a337244544},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18093. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a general method for estimating entropy differences between arbitrary probability distributions using stochastic interpolants. The marginal distributions which bridge the base and target obey a continuity equation, which allows a straightforward calculation of the entropy difference in terms of an inner product of the probability flow velocity and score fields. This formulation has several advantages: (i) no computationally expensive divergence calculations of either field are required, (ii) the score field need not even be learned directly if model transferability is not required, and (iii) on-the-fly estimates are produced nearly for free during training. When tractable base distributions are chosen (e.g. Gaussian chain, ideal gas, etc.), statistical thermodynamic entropies are then immediately recovered. Notably, the analysis relies only on the definition of the Gibbs-Shannon entropy, rather than any particular statistical mechanical ensemble, so that generalized non-equilibrium entropies may be computed. The method is demonstrated on several systems of increasing complexity: (i) a 40-dimensional Gaussian mixture model, (ii) the classical XY model of N spins arranged in one dimension, (iii) the 13-atom Lennard-Jones cluster, and (iv) an active Brownian polymer.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-17 in cond-mat.stat-mech).
Categorie arXiv: Statistical Mechanics (cond-mat.stat-mech) ; Chemical Physics (physics.chem-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.18093 — 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 2026-10-15T17:06:03.911Z dalla pagina https://arxiv.org/catchup/cond-mat.stat-mech/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).