Metraipolis › archive › dc_52bf778dad81

Improving score-based sampling via affine post-processing — arXiv:2610.04773

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.04773
License (as archived)
CC0-1.0
Archived
2026-10-06T09:36:19.918Z
SHA-256 of the archived text
10f3568ca6576d46ecf919a526f9df95e9ba61608579c86a9fb38e7749575a2d
Stable URL of this page
https://metraipolis.com/documento/dc_52bf778dad81

How to cite

Improving score-based sampling via affine post-processing — arXiv:2610.04773 — arXiv (en), https://arxiv.org/abs/2610.04773 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_52bf778dad81 (Metraipolis archive dc_52bf778dad81, sha256 10f3568ca6576d46ecf919a526f9df95e9ba61608579c86a9fb38e7749575a2d)
BibTeX
@misc{dc52bf778dad81,
  title = {Improving score-based sampling via affine post-processing — arXiv:2610.04773},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.04773},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_52bf778dad81; sha256 10f3568ca6576d46ecf919a526f9df95e9ba61608579c86a9fb38e7749575a2d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.04773. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sampling from a probability distribution with access only to its log-density is a foundational problem in statistics, machine learning, and the physical sciences. This problem is studied in the data-free score-based diffusion literature, which samples the target density via estimating scores of densities produced by convolution with Gaussian random variables and implementing a reverse SDE. In this framework, score estimators are constructed via Markov chain Monte Carlo, importance sampling, or rejection sampling. The estimators often operate far beyond the regime where mixing time and error control can be established and have large bias and variance when estimating the underlying score. In our method we propose post-processing: splitting a fixed computation budget across multiple evaluations, querying the estimator at different points, and fitting a single pooled estimate via linear combination to minimize bias and variance at a target location. The final value is an affine map of a vector of multiple score estimates. We show this reduces score estimation error when compared to the computation-matched base estimator queried at a single point. We demonstrate improved sample quality over other score estimation methods matched for computation cost on difficult target densities such as log-concave densities with large condition number, multimodal densities, and high-dimensional densities.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ME, nuovi lavori del giorno).
Categorie arXiv: Methodology (stat.ME) ; Computation (stat.CO).
Pagina del lavoro: https://arxiv.org/abs/2610.04773 — 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 2026-10-06T08:24:29.081Z dalla pagina https://arxiv.org/list/stat.ME/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).