Metraipolis › archive › dc_867f2d6da2cf

One-Step Generative Surrogate Models via Block-Triangular Joint Drifting — arXiv:2609.26435

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26435
License (as archived)
CC0-1.0
Archived
2026-10-08T15:08:00.285Z
SHA-256 of the archived text
ee922f254dedbd72999ef122bc478df655a79584520c33bce395e740fffb52d5
Stable URL of this page
https://metraipolis.com/documento/dc_867f2d6da2cf

How to cite

One-Step Generative Surrogate Models via Block-Triangular Joint Drifting — arXiv:2609.26435 — arXiv (en), https://arxiv.org/abs/2609.26435 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_867f2d6da2cf (Metraipolis archive dc_867f2d6da2cf, sha256 ee922f254dedbd72999ef122bc478df655a79584520c33bce395e740fffb52d5)
BibTeX
@misc{dc867f2d6da2cf,
  title = {One-Step Generative Surrogate Models via Block-Triangular Joint Drifting — arXiv:2609.26435},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26435},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_867f2d6da2cf; sha256 ee922f254dedbd72999ef122bc478df655a79584520c33bce395e740fffb52d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26435. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of the next state conditioned on the same current state. Standard trajectory data, however, typically provide only one realized next state for each observed current state and therefore do not provide an empirical approximation of the corresponding conditional distribution over possible next states. We introduce block-triangular joint drifting, which instead applies a projected drift field to the empirically accessible joint distribution of consecutive states. Importantly, the block-triangular architecture preserves the current-state marginal while making its second component a direct sampler of the conditional distribution of possible next states. The resulting surrogate generates stochastic trajectories with one model evaluation per time step, without auxiliary generative steps between time steps. Numerical experiments demonstrate accurate marginal and trajectory-dependent statistics and favorable accuracy-cost tradeoffs compared with deterministic, diffusion-, flow-, and distillation-based generative surrogate models.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2609.26435 — 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 2026-10-08T14:37:29.491Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).