EUVIMEDEUVIMED entdecken
Crossref

Schrödinger-Föllmer Sampler

Jian Huang, Yuling Jiao, Lican Kang, Xu Liao, Jin Liu, Yanyan Liu

IEEE Transactions on Information Theory · 2025-02 · 71 (2) · 1283-1299

DOI: 10.1109/tit.2024.3522494 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2025-02. Verfasst von Jian Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 85 Literaturangaben. Gefördert von: Guangdong Provincial Key Laboratory of Mathematical Foundations for Artificial Intelligence, Shenzhen Key Laboratory of Cross-Modal Cognitive Computing, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sampling from probability distributions is a critical problem in statistics and machine learning, particularly in Bayesian inference, where direct integration over the posterior distribution is often infeasible, making sampling from the posterior essential for inference. This paper introduces the Schrödinger-Föllmer sampler (SFS), a novel approach for sampling from potentially unnormalized distributions. The SFS leverages the Schrödinger-Föllmer diffusion process on the unit interval, incorporating a time-dependent drift term that evolves the distribution from a degenerate form at time zero to the target distribution at time one. Unlike existing Markov chain Monte Carlo methods that rely on ergodicity, SFS operates independently of ergodicity. Computationally, SFS is straightforward to implement using the Euler-Maruyama discretization. In our theoretical analysis, we derive non-asymptotic error bounds for the SFS sampling distribution in the Wasserstein distance, subject to reasonable conditions. Numerical experiments demonstrate that SFS generates higher-quality samples than several established methods.

Förderung

  • Guangdong Provincial Key Laboratory of Mathematical Foundations for Artificial Intelligence
  • Shenzhen Key Laboratory of Cross-Modal Cognitive Computing
  • National Natural Science Foundation of China
  • Hong Kong Polytechnic University
  • Fundamental Research Funds for the Central Universities
  • University Development Fund from The Chinese University of Hong Kong, Shenzhen

Zitieren

APA

Huang, J., Jiao, Y., Kang, L., Liao, X., Liu, J., & Liu, Y. (2025). Schrödinger-Föllmer Sampler. IEEE Transactions on Information Theory, 71(2), 1283-1299. https://doi.org/10.1109/tit.2024.3522494

Vancouver

Huang J, Jiao Y, Kang L, Liao X, Liu J, Liu Y. Schrödinger-Föllmer Sampler. IEEE Transactions on Information Theory. 2025;71(2):1283-1299. doi:10.1109/tit.2024.3522494

BibTeX
@article{Huang2025,
  author = {Huang, Jian and Jiao, Yuling and Kang, Lican and Liao, Xu and Liu, Jin and Liu, Yanyan},
  title = {Schrödinger-Föllmer Sampler},
  journal = {IEEE Transactions on Information Theory},
  year = {2025},
  volume = {71},
  number = {2},
  pages = {1283--1299},
  doi = {10.1109/tit.2024.3522494}
}
Kostenlos starten →